Information configuration method and apparatus, electronic device, and storage medium

Abstract

An information configuration method and apparatus, an electronic device, and a storage medium. The information configuration method comprises: preprocessing historical product data to obtain feature data of a feature field and attribute data of an attribute field (S110); calculating a data distance of the attribute data corresponding to the feature data, wherein the data distance represents the similarity between the attribute data corresponding to the feature data and corresponding full attribute data (S120); and on the basis of the attribute data that is the same as or has the greatest similarity to feature data of a target product, configuring target attribute data of the target product (S130).

Description

Information configuration method, device, electronic device and storage medium Technical Field

[0001] The embodiments of this specification belong to the field of database management technology, and in particular, relate to an information configuration method, device, electronic device, and storage medium. Background Art

[0002] Internet product rules are a set of regulations and guiding principles for the design, development, operation, and promotion of internet products and services. By analyzing these rules, companies can understand user behavior and needs, identify product or service issues and bottlenecks, optimize their products and services, and develop more effective marketing and promotion strategies. However, optimizing processes and resource allocation to effectively apply these rules remains a major technical challenge.

[0003] Summary of the Invention

[0004] In a first aspect, an embodiment of the present specification provides an information configuration method, including: preprocessing historical product data to obtain feature data of feature fields and attribute data of attribute fields; calculating the data distance of the attribute data corresponding to the feature data; the data distance represents the similarity between the attribute data corresponding to the feature data and the corresponding full attribute data; and configuring the target attribute data of the target product based on the attribute data that is identical to the feature data of the target product and has the greatest similarity.

[0005] In the second aspect, an embodiment of this specification provides an information configuration device, including: a processing module for preprocessing historical product data to obtain feature data of feature fields and attribute data of attribute fields; a calculation module for calculating the data distance of the attribute data corresponding to the feature data; the data distance represents the similarity between the attribute data corresponding to the feature data and the corresponding full attribute data; a configuration module for configuring the target attribute data of the target product based on the attribute data that is the same as the feature data of the target product and has the greatest similarity.

[0006] In a third aspect, an embodiment of this specification further provides an electronic device, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned information configuration method steps.

[0007] In a fourth aspect, an embodiment of this specification provides a computer storage medium, which stores a plurality of instructions suitable for being loaded by a processor and executing the above-mentioned information configuration steps.

[0008] The beneficial effects brought about by the technical solutions provided in some embodiments of this specification include at least: in one or more embodiments of this specification, after preprocessing the historical product data, the similarity of the attribute data corresponding to the feature data is calculated, and the target attribute data of the target product is configured based on the attribute data with the highest similarity, thereby reducing the errors that may occur in manual configuration and improving the efficiency and accuracy of data configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0010] FIG1 is a schematic diagram of a system architecture of an information configuration method provided in an embodiment of this specification.

[0011] FIG2 is a schematic diagram of the structure of an information configuration device provided in an embodiment of this specification.

[0012] FIG3 is a schematic structural diagram of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0013] The technical solutions in the embodiments of this specification will be described clearly and completely below in conjunction with the drawings in the embodiments of this specification.

[0014] Throughout this specification, the claims, and the accompanying drawings, the terms "first," "second," "third," and the like are used to distinguish between different items, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may include other steps or elements inherent to the process, method, product, or apparatus.

[0015] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of this specification. Various examples may appropriately omit, replace, or add various processes or components. For example, the described methods may be performed in an order different from the order described, and various steps may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined in other examples.

[0016] In order to better understand the present invention, before describing the present invention, the meanings of the terms appearing in the text are first explained.

[0017] A data dictionary is a set of data items (data elements, the basic unit of data and the smallest indivisible unit of data) in a database, arranged in a specific order and providing a detailed description of their contents. The data dictionary contains definitions of all data in the system, that is, descriptions of all database structures. It is a shared repository that defines the meaning, type, data size, format, unit of measurement, precision, and allowed value range of all data elements and structures used in the database. The data dictionary is represented by tables in the database.

[0018] In databases, table columns are often called fields, and each field contains information about a specific topic. For example, in an address book database, "name" and "contact number" are attributes shared by all rows in the table, so these columns can be called the "name" field and the "contact number" field.

[0019] A key-value pair is a programming language's implementation of a mathematical concept called a mapping. The key serves as an index to an element, while the value represents the data being stored and retrieved. In this disclosure, key is represented by feature data, and value is represented by attribute data.

[0020] A hash algorithm, or hash function, transforms an input of arbitrary length into an output of fixed length. A hash table is a mapping from one set A to another set B, a correspondence that is common in real life, for example, A → B; person → identity information; date → zodiac sign. In a hash table, this correspondence is called hashing. Element a in set A corresponds to element b in set B, and b is called the hash value of a.

[0021] Please refer to FIG1 , which shows an overall flow chart of an information configuration method provided by an embodiment of this specification.

[0022] As shown in FIG. 1 , the information configuration method may at least include steps S110 to S130 .

[0023] Step S110 , pre-processing the historical product data to obtain feature data of feature fields and attribute data of attribute fields.

[0024] The historical product data described in this embodiment may refer to data generated during the operation of the corresponding platform or system. These data often include data related to characteristic attributes. For example, the transaction data generated in the trading platform includes transaction characteristic related data such as order source, order type, account type, etc. At the same time, these data also include attribute data related to characteristic data. For example, the transaction data generated in the trading platform includes transaction characteristic related data such as transaction amount, account number, serial number, transaction time, transaction status, etc.

[0025] It should be noted that the feature field and attribute field in this embodiment are fields containing feature information and attribute information respectively, wherein the feature data can be part of the feature field, or a summary of the feature field, or the same as the feature field; correspondingly, the attribute data can be part of the attribute field, or a summary of the attribute field, or the same as the attribute field.

[0026] Taking insurance product data as an example, feature data can include insurance product type, the institution to which the insurance product belongs, etc. Attribute data can include product purchase restrictions, age restrictions, amount restrictions, payment channels, coverage period, surrender configurations, renewal configurations, and supplementary insurance rules. Based on industry experience, the rules for the top 500 insurance products ranked by data analysis can cover over 98% of products, while covering 100% of insurance products requires the rules for the top 1000 insurance products. For most insurance products, establishing a 1000-dimensional data vector library requires a significant amount of computational effort and yields limited benefits. Therefore, a comprehensive analysis can select a 500-dimensional vector, i.e., the product data for the top 500 insurance products, as the historical product data in this embodiment.

[0027] In one example, the purchase restriction rule may be a quantity restriction, such as most medical and serious illness products have quantity restriction rules, and most products limit the same user to only one copy. Age restrictions include restrictions on the age of the policyholder and the age of the insured. For example, the policyholder cannot be less than 18 years old and must be a person with full civil capacity. Children's insurance requires that the insured cannot be older than 18 years old, and major disease insurance requires that the insured cannot be older than 55 years old. Amount restrictions, such as the insured amount of children's accident insurance cannot exceed 100,000 yuan. Here, only some attribute data are exemplified, and the specific numerical description may vary based on the specific insurance rules, and there is no restriction on this. Other attribute data may not be enumerated.

[0028] In some possible embodiments, step S110 preprocesses the historical product data to obtain characteristic data of characteristic fields and attribute data of attribute fields, including: unifying the historical product data by hierarchical standards to obtain characteristic data of characteristic fields and attribute data of attribute fields.

[0029] Taking insurance product data as an example, by classifying insurance products based on their characteristic insured objects, we can categorize them into four types: property insurance, personal insurance, liability insurance, and credit insurance. Property insurance covers material wealth and related interests, and can include marine insurance, cargo insurance, engineering insurance, aviation insurance, fire insurance, automobile insurance, household contents insurance, theft insurance, business interruption insurance, and agricultural insurance. Personal insurance covers the human body, and can include personal accident insurance, illness insurance, and life insurance (including death, survival, and endowment insurance). Liability insurance covers the insured's civil liability for damages. Any legal financial liability of the insured for damages to others is borne by the insurer and is generally supplemented with indemnity insurance, such as collision liability in marine insurance, automobile insurance, aircraft insurance, and engineering insurance. Credit insurance is a type of insurance that covers the third party's performance of its obligations to the insured. It includes fidelity bond insurance and performance insurance. Here, fidelity bond insurance covers the employer's losses caused by the illegal acts of its employees, and performance insurance covers the economic liability of one party to the contract for breach of contract.

[0030] Taking into account the differences in rules for insurance products of different types and levels, it is necessary to unify the hierarchical standards of insurance product data, that is, unify the types and names to ensure that historical product data is in the same dimension.

[0031] In this embodiment, by unifying the hierarchical standards of historical product data, the differences between the data are reduced and the accuracy of subsequent calculations is ensured.

[0032] In some possible embodiments, in step S110, after preprocessing the historical product data to obtain the feature data of the feature field and the attribute data of the attribute field, the method further includes: normalizing the attribute data to obtain corresponding normalized values; and eliminating the attribute data whose normalized values ​​exceed a preset range.

[0033] Normalization is a dimensionless processing method, that is, a dimensional expression is transformed into a dimensionless expression and becomes a scalar.

[0034] In this embodiment, the attribute data is vectorized in advance and then normalized to obtain a series of normalized values ​​for further screening. It should be noted that the preset range can be determined based on experience or accuracy requirements and is not specifically limited here.

[0035] For example, for the product data of the top 500 insurance products, some product rules are more commonly used and appear very frequently, while some product rules are uncommon and appear very rarely. Therefore, the normalized values ​​obtained after normalization may be quite different. For example, the value of a high frequency of occurrence may reach 0.5, while the value of a low frequency of occurrence may be less than 0.05. Therefore, by eliminating some data with too low a frequency of occurrence, the range of the attribute data can be further improved.

[0036] Step S120 , calculating the data distance of the attribute data corresponding to the feature data; the data distance represents the similarity between the attribute data corresponding to the feature data and the corresponding full attribute data.

[0037] In this embodiment, the data distance between the attribute data corresponding to the feature data is calculated to determine the similarity corresponding to each attribute data.

[0038] In some possible embodiments, step S120, calculating the data distance of the attribute data corresponding to the feature data, includes: quantizing the feature data and the attribute data to obtain feature vector data and attribute vector data; and calculating the data distance of the attribute vector data corresponding to the feature vector data.

[0039] In this embodiment, the attribute data converted into vectors may be processed by a vector calculation engine to obtain the data distance of the attribute data corresponding to the feature data.

[0040] Exemplarily, after extracting the feature vectors corresponding to each attribute data, the similarity between the feature vectors corresponding to each attribute data and the feature vector corresponding to the full attribute data is calculated. In order to improve the accuracy of the similarity calculation, the embodiment of the present application uses the cosine distance algorithm to calculate the similarity between the feature vectors corresponding to each attribute data. Generally, if the angle between two feature vectors is substantially the same, it can be considered that the similarity between the two feature vectors is relatively large. Of course, the embodiment of the present application can also use other similarity algorithms, such as the sine distance algorithm, etc., which are not limited here.

[0041] In some possible embodiments, step S120, calculating the data distance of the attribute data corresponding to the feature data, includes: obtaining the full attribute data corresponding to the historical product data with the same feature data; calculating the similarity between the attribute data corresponding to each feature data and the full attribute data, and obtaining the corresponding data distance.

[0042] In this embodiment, the similarity represents the proportion of the attribute data corresponding to the feature data in the corresponding total attribute data. The larger the proportion, the higher the similarity.

[0043] For example, for a particular insurance product, due to different launching institutions, there are often some differences in the various rules and clauses. Taking the sampling of the rules of the top 500 insurance products as an example, assuming that the full attribute data includes a piece of attribute data, after preprocessing, the full attribute data containing b pieces of attribute data is obtained. If insurance product X includes c pieces of attribute data, and these c pieces of attribute data all appear in the quantitative attribute data, then the similarity between the attribute data of insurance product X and the corresponding full attribute data can be obtained as c / b. Therefore, the similarity c / b can be determined as the data distance of the attribute data.

[0044] In some possible embodiments, obtaining the full amount of attribute data corresponding to historical product data with the same feature data also includes: constructing a feature data dictionary and an attribute data dictionary based on the feature data and the attribute data, respectively; each feature data in the feature data dictionary has a mapping relationship with at least one attribute data in the attribute data dictionary; obtaining all attribute data that have a mapping relationship with the same feature data as the full amount of attribute data of the feature data.

[0045] In this embodiment, a feature data dictionary can be pre-built based on the feature data, and an attribute data dictionary can be built based on the attribute data. These dictionary structures are key and value dictionaries. A mapping relationship exists between the key and value dictionaries. Each key value in the key dictionary has one or more corresponding values ​​in the value dictionary. This means that each feature data item in the feature data table has one or more corresponding attribute data sets in the attribute data table. Here, a set of key-value pairs is built for each feature type to determine the full set of attribute data corresponding to each feature type.

[0046] In some possible embodiments, after obtaining the full amount of attribute data corresponding to the historical product data with the same characteristic data, the method further includes: filtering the attribute data in the full amount of attribute data based on the frequency of occurrence of the data, and eliminating the attribute data with an occurrence frequency less than a preset threshold.

[0047] For example, assume that the full attribute data includes a piece of attribute data. After preprocessing, the full attribute data includes b pieces of attribute data. The full attribute data is then screened to remove attribute data with a frequency of occurrence below a preset threshold, resulting in the full attribute data including c pieces of attribute data. If insurance product Y includes d pieces of attribute data, and all of these d pieces of attribute data appear in the attribute data, the similarity between the attribute data of insurance product Y and the corresponding full attribute data is d / c. Therefore, the similarity d / c can be determined as the data distance of the attribute data. By screening the full attribute data, invalid data can be further reduced and the reliability of the full attribute data can be improved.

[0048] Step S130 , configuring target attribute data of the target product based on attribute data that is identical to and has the greatest similarity to the feature data of the target product.

[0049] In this embodiment, the target product's feature data is vectorized to determine its similarity to the full attribute data. Compared to the full attribute data, the target product's feature data may partially exist in the full attribute data, while others may be new attribute data. In this case, historical products of the same type and name that share the same similarity as the target product can be searched for, that is, the historical product data with the highest similarity is found. Based on this historical product's attribute data, the target product's attribute data can be adjusted and matched.

[0050] In some possible embodiments, before configuring the target attribute data of the target product based on the attribute data that is identical to and has the greatest similarity to the feature data of the target product in step S130, the method includes: sorting the attribute data corresponding to the same feature data according to data distance to obtain attribute data sorting information corresponding to each feature data.

[0051] In this embodiment, after determining the similarity corresponding to the characteristic data of the target product, multiple products similar to the target product can be screened from the historical products. These historical products have a high degree of similarity with the target product and can therefore serve as the basis for configuring the target attribute data corresponding to the target product. These attribute data can also be sorted based on the similarity, with the higher the ranking, the greater the similarity.

[0052] In some possible embodiments, step S130 configures the target attribute data of the target product based on attribute data that is identical to and has the greatest similarity to the characteristic data of the target product, including: querying attribute data sorting information based on the characteristic data of the target product to determine the target attribute data sorting information corresponding to the characteristic data of the target product; and configuring the target attribute data of the target product based on the attribute data with the greatest similarity in the target attribute data sorting information.

[0053] In this embodiment, the target attribute data of the target product is configured based on the aforementioned ranking information. The target attribute data of the target product can be configured based on the attribute data with the greatest similarity in the ranking information. Alternatively, each attribute data in the ranking information can be weighted, with the higher the ranking, the greater the corresponding weight. Thus, the target attribute data of the target product is comprehensively configured based on each attribute data in the ranking information.

[0054] In one example, the corresponding target attribute data can be output based on a hash algorithm. Using the target product's current feature data and attribute data as input, the algorithm outputs one or more historical products with the highest similarity and their corresponding attribute data. The target attribute data for the target product is then comprehensively configured based on the attribute data corresponding to these historical products.

[0055] The embodiment of the present application pre-processes historical product data and calculates the similarity of attribute data corresponding to the feature data, thereby configuring the target attribute data of the target product based on the attribute data with the highest similarity, thereby reducing errors that may occur in manual configuration and improving the efficiency and accuracy of data configuration.

[0056] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0057] Next, please refer to Figure 2, which shows a schematic diagram of the structure of an information configuration device provided in an embodiment of this specification. It should be noted that the information configuration device shown in Figure 2 is used to execute the method of the embodiment shown in Figure 1 of this application. For ease of explanation, only the parts related to the embodiment of this application are shown. For specific technical details not disclosed, please refer to the embodiment shown in Figure 1 of this application.

[0058] As shown in FIG2 , the information configuration device 200 may include at least a processing module 210 , a calculation module 220 and a configuration module 230 , wherein the processing module 210 is used to pre-process historical product data to obtain feature data of feature fields and attribute data of attribute fields.

[0059] The historical product data described in this embodiment may refer to data generated during the operation of a feature platform or a feature system. These data often include data related to feature attributes. For example, the transaction data generated in the trading platform includes transaction attribute-related data such as order source, order type, and account type. At the same time, these data also include attribute data related to feature data. For example, the transaction data generated in the trading platform includes transaction feature-related data such as transaction amount, account number, serial number, transaction time, and transaction status.

[0060] It should be noted that the feature field and attribute field in this embodiment are fields containing feature information and attribute information respectively, wherein the feature data can be part of the feature field, or a summary of the feature field, or the same as the feature field; correspondingly, the attribute data can be part of the attribute field, or a summary of the attribute field, or the same as the attribute field.

[0061] In some possible embodiments, the processing module 210 is used to: unify the historical product data into hierarchical standards, and obtain feature data of feature fields and attribute data of attribute fields.

[0062] Considering the differences in regulations across different types and tiers of insurance products, it's necessary to standardize insurance product data across different hierarchies. This means unifying types and names to ensure that historical product data is consistent across dimensions. This standardization reduces data disparity and ensures the accuracy of subsequent calculations.

[0063] In some possible embodiments, the processing module 210 is further configured to: perform normalization processing on the attribute data to obtain corresponding normalized values; and eliminate attribute data whose normalized values ​​exceed a preset range.

[0064] In this embodiment, the attribute data is vectorized in advance and then normalized to obtain a series of normalized values ​​for further screening. It should be noted that the preset range can be determined based on experience or accuracy requirements and is not specifically limited here.

[0065] The calculation module 220 is used to calculate the data distance of the attribute data corresponding to the feature data; the data distance represents the similarity between the attribute data corresponding to the feature data and the corresponding full attribute data.

[0066] In this embodiment, the data distance between the attribute data corresponding to the feature data is calculated to determine the similarity corresponding to each attribute data.

[0067] In some possible embodiments, the calculation module 220 is further used to: obtain the full attribute data corresponding to the historical product data with the same feature data; calculate the similarity between the attribute data corresponding to each feature data and the full attribute data to obtain the corresponding data distance.

[0068] In this embodiment, the attribute data converted into vectors may be processed by a vector calculation engine to obtain the data distance of the attribute data corresponding to the feature data.

[0069] Exemplarily, after extracting the feature vectors corresponding to each attribute data, the similarity between the feature vectors corresponding to each attribute data and the feature vector corresponding to the full attribute data is calculated. In order to improve the accuracy of the similarity calculation, the embodiment of the present application uses the cosine distance algorithm to calculate the similarity between the feature vectors corresponding to each attribute data. Generally, if the angle between two feature vectors is substantially the same, it can be considered that the similarity between the two feature vectors is relatively large. Of course, the embodiment of the present application can also use other similarity algorithms, such as the sine distance algorithm, etc., which are not limited here.

[0070] In some possible embodiments, the calculation module 220 is also used to: construct a feature data dictionary and an attribute data dictionary based on the feature data and the attribute data, respectively; each feature data in the feature data dictionary has a mapping relationship with at least one attribute data in the attribute data dictionary; and obtain all attribute data that have a mapping relationship with the same feature data as the full attribute data of the feature data.

[0071] In this embodiment, a feature data dictionary can be pre-built based on the feature data, and an attribute data dictionary can be built based on the attribute data. These dictionary structures are key and value dictionaries. A mapping relationship exists between the key and value dictionaries. Each key value in the key dictionary has one or more corresponding values ​​in the value dictionary. This means that each feature data item in the feature data table has one or more corresponding attribute data sets in the attribute data table. Here, a set of key-value pairs is built for each feature type to determine the full set of attribute data corresponding to each feature type.

[0072] In some possible embodiments, a screening module is further included, which is used to screen the attribute data in the full amount of attribute data based on the frequency of occurrence of the data, and eliminate the attribute data with an occurrence frequency less than a preset threshold.

[0073] For example, assume that the full attribute data includes a piece of attribute data. After preprocessing, the full attribute data includes b pieces of attribute data. The full attribute data is then screened to remove attribute data with a frequency of occurrence below a preset threshold, resulting in the full attribute data including c pieces of attribute data. If insurance product Y includes d pieces of attribute data, and all of these d pieces of attribute data appear in the attribute data, the similarity between the attribute data of insurance product Y and the corresponding full attribute data is d / c. Therefore, the similarity d / c can be determined as the data distance of the attribute data. By screening the full attribute data, invalid data can be further reduced and the reliability of the full attribute data can be improved.

[0074] The configuration module 230 is configured to configure target attribute data of the target product based on attribute data that is identical to and has the greatest similarity to the feature data of the target product.

[0075] In this embodiment, the target product's feature data is vectorized to determine its similarity to the full attribute data. Compared to the full attribute data, the target product's feature data may partially exist in the full attribute data, while others may be new attribute data. In this case, historical products of the same type and name that share the same similarity as the target product can be searched for, that is, the historical product data with the highest similarity is found. Based on this historical product's attribute data, the target product's attribute data can be adjusted and matched.

[0076] In some possible embodiments, a sorting module is further included, and the sorting module is used to sort the attribute data corresponding to the same feature data according to the data distance to obtain attribute data sorting information corresponding to each feature data.

[0077] In this embodiment, after determining the similarity corresponding to the characteristic data of the target product, multiple products similar to the target product can be screened from the historical products. These historical products have a high degree of similarity with the target product and can therefore serve as the basis for configuring the target attribute data corresponding to the target product. These attribute data can also be sorted based on the similarity, with the higher the ranking, the greater the similarity.

[0078] In some possible embodiments, the configuration module 230 is used to: query attribute data sorting information based on the characteristic data of the target product, determine the target attribute data sorting information corresponding to the characteristic data of the target product; and configure the target attribute data of the target product based on the attribute data with the greatest similarity in the target attribute data sorting information.

[0079] In this embodiment, the target attribute data of the target product is configured based on the aforementioned ranking information. The target attribute data of the target product can be configured based on the attribute data with the greatest similarity in the ranking information. Alternatively, each attribute data in the ranking information can be weighted, with the higher the ranking, the greater the corresponding weight. Thus, the target attribute data of the target product is comprehensively configured based on each attribute data in the ranking information.

[0080] In one example, the corresponding target attribute data can be output based on a hash algorithm. Using the target product's current feature data and attribute data as input, the algorithm outputs one or more historical products with the highest similarity and their corresponding attribute data. The target attribute data for the target product is then comprehensively configured based on the attribute data corresponding to these historical products.

[0081] Those skilled in the art will clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently perform or cooperate with other components to perform specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0082] Each processing unit and / or module in the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0083] Next, please refer to FIG3 , which shows a schematic structural diagram of an electronic device provided in an embodiment of this specification.

[0084] As shown in FIG. 3 , the electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0085] The communication bus 302 may be used to implement the connection and communication between the above components.

[0086] The user interface 303 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0087] The network interface 304 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, and the like.

[0088] The processor 301 may include one or more processing cores. The processor 301 utilizes various interfaces and lines to connect the various parts of the entire information configuration device 200, and executes various functions and processes data of the routing information configuration device 200 by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 may be implemented in at least one hardware form of DSP, FPGA, and PLA. The processor 301 may integrate one or a combination of CPU, GPU, and modem. The CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used to handle wireless communications. It is understandable that the above-mentioned modem may not be integrated into the processor 301, but may be implemented separately through a chip.

[0089] Among them, the memory 305 may include RAM and may also include ROM. Optionally, the memory 305 includes a non-transitory computer-readable medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also be at least one storage device located away from the aforementioned processor 301. As shown in Figure 3, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and program instructions.

[0090] Specifically, the processor 301 can be used to call the information configuration method application stored in the memory 305, and perform the following operations: preprocess the historical product data to obtain the feature data of the feature field and the attribute data of the attribute field; calculate the data distance of the attribute data corresponding to the feature data; the data distance represents the similarity between the attribute data corresponding to the feature data and the corresponding full attribute data; configure the target attribute data of the target product based on the attribute data that is the same as the feature data of the target product and has the greatest similarity.

[0091] In some possible embodiments, the method steps described in other embodiments of the information configuration method may also be executed.

[0092] The embodiments of this specification also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above method. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a microdrive, a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic or optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0093] 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.

[0094] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely 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 service interface, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0096] 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.

[0097] 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.

[0098] 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 memory. Based on this understanding, the technical solution of the present application is essentially 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, and the computer software product is stored in a memory, including a number of 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 memory includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0099] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0100] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An information configuration method, comprising: Preprocess the historical product data to obtain feature data of feature fields and attribute data of attribute fields; Calculating a data distance of the attribute data corresponding to the feature data; the data distance represents a similarity between the attribute data corresponding to the feature data and the corresponding full attribute data; The target attribute data of the target product is configured based on the attribute data which is identical to the feature data of the target product and has the greatest similarity.

2. The method according to claim 1, wherein: The preprocessing of the historical product data to obtain the feature data of the feature field and the attribute data of the attribute field includes: The historical product data is unified by hierarchical standards to obtain feature data of feature fields and attribute data of attribute fields.

3. The method according to claim 1, wherein: After preprocessing the historical product data to obtain the feature data of the feature field and the attribute data of the attribute field, the method further includes: Normalizing the attribute data to obtain corresponding normalized values; The attribute data whose normalized values ​​exceed a preset range are eliminated.

4. The method according to claim 1, wherein: The calculating the data distance of the attribute data corresponding to the feature data includes: Acquire the full amount of attribute data corresponding to the historical product data having the same characteristic data; The similarity between the attribute data corresponding to each feature data and the full attribute data is calculated to obtain the corresponding data distance.

5. The method according to claim 4, wherein: The obtaining of the full amount of attribute data corresponding to the historical product data having the same characteristic data also includes: Based on the feature data and the attribute data, a feature data dictionary and an attribute data dictionary are respectively constructed; each feature data in the feature data dictionary has a mapping relationship with at least one attribute data in the attribute data dictionary; All attribute data that are mapped to the same feature data are acquired as the full attribute data of the feature data.

6. The method according to claim 4, wherein: After obtaining the full amount of attribute data corresponding to the historical product data having the same characteristic data, the method further includes: The attribute data in the total attribute data are screened based on the occurrence frequency of the data, and the attribute data with an occurrence frequency less than a preset threshold is eliminated.

7. The method according to claim 1, wherein: The calculating the data distance of the attribute data corresponding to the feature data includes: Quantizing the feature data and the attribute data to obtain feature vector data and attribute vector data; The data distance of the attribute vector data corresponding to the feature vector data is calculated.

8. The method according to claim 1, wherein: Before configuring the target attribute data of the target product based on the attribute data that is identical to the feature data of the target product and has the greatest similarity, the method includes: The attribute data corresponding to the same feature data are sorted according to the data distance to obtain attribute data sorting information corresponding to each feature data.

9. The method according to claim 8, wherein: The configuring the target attribute data of the target product based on the attribute data which is identical to the feature data of the target product and has the greatest similarity includes: Querying the attribute data sorting information according to the characteristic data of the target product to determine the target attribute data sorting information corresponding to the characteristic data of the target product; The target attribute data of the target product is configured based on the attribute data with the greatest similarity in the target attribute data sorting information.

10. An information configuration device, comprising: A processing module, used for preprocessing the historical product data to obtain feature data of feature fields and attribute data of attribute fields; A calculation module, used for calculating a data distance of the attribute data corresponding to the feature data; the data distance represents a similarity between the attribute data corresponding to the feature data and corresponding full attribute data; The configuration module is used to configure the target attribute data of the target product based on the attribute data that is the same as the feature data of the target product and has the greatest similarity.

11. The device according to claim 10, wherein: The processing module is used for: The historical product data is unified by hierarchical standards to obtain feature data of feature fields and attribute data of attribute fields.

12. The device according to claim 10, wherein: The processing module is also used for: Normalizing the attribute data to obtain corresponding normalized values; The attribute data whose normalized values ​​exceed a preset range are eliminated.

13. The device according to claim 10, wherein: The calculation module is also specifically used for: Acquire the full amount of attribute data corresponding to the historical product data having the same characteristic data; The similarity between the attribute data corresponding to each feature data and the full attribute data is calculated to obtain the corresponding data distance.

14. The device according to claim 13, wherein: The calculation module is also specifically used for: Based on the feature data and the attribute data, a feature data dictionary and an attribute data dictionary are respectively constructed; each feature data in the feature data dictionary has a mapping relationship with at least one attribute data in the attribute data dictionary; All attribute data that are mapped to the same feature data are acquired as the full attribute data of the feature data.

15. The device according to claim 13, further comprising a screening module, wherein the screening module is used to: The attribute data in the total attribute data are screened based on the occurrence frequency of the data, and the attribute data with an occurrence frequency less than a preset threshold is eliminated.

16. The device according to claim 10, wherein: The calculation module is used for: Quantizing the feature data and the attribute data to obtain feature vector data and attribute vector data; The data distance of the attribute vector data corresponding to the feature vector data is calculated.

17. The apparatus according to claim 10, further comprising a sorting module, wherein the sorting module is configured to: The attribute data corresponding to the same feature data are sorted according to the data distance to obtain attribute data sorting information corresponding to each feature data.

18. The device according to claim 17, wherein: The configuration module is used to: Querying the attribute data sorting information according to the characteristic data of the target product to determine the target attribute data sorting information corresponding to the characteristic data of the target product; The target attribute data of the target product is configured based on the attribute data with the greatest similarity in the target attribute data sorting information.

19. An electronic device comprising a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to any one of claims 1 to 9.

20. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium has instructions stored therein, and when the instructions are executed on a computer or a processor, the computer or the processor executes the method according to any one of claims 1 to 9.

Images