A market-assisted decision system based on big data

Abstract

The application relates to the computer technical field, in particular to a market auxiliary decision-making system based on big data, which comprises a receiving terminal used for receiving current user cataloging mark information and browsing data information of URL addresses of any webpage on each terminal website; a processing module used for determining the perfection degree of entry in the cataloging mark information and determining a first recommendation list based on the current user according to the perfection degree of the entry in the cataloging mark information; a storage module used for storing and summarizing the browsing data information of the user on at least one terminal website, summarizing historical state parameter information, and storing product database information on the terminal website; and an analysis module used for determining a second recommendation list according to the historical state parameter information and the product database information, and determining a target recommendation list according to the coincident items of the first recommendation list and the second recommendation list. The application realizes fine recommendation of related product information.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a market auxiliary decision-making system based on big data. BACKGROUND

[0002] Big data is a data collection with the main characteristics of large capacity, multiple types, fast access speed and high application value. It can collect, store and correlate analyze the data with huge quantity, scattered source and various formats, and find new knowledge, create new value and enhance new ability from it. Big data is an important application field of cosmetic production industry. Due to the difference between individuals, users also have many personalized requirements when choosing cosmetics. Therefore, with the progress of computer technology, the analysis of big data provides a new way for the solution of many cosmetic production problems.

[0003] The patent with publication number CN112905877A discloses a cosmetic information detection method based on cloud computing and a cosmetic e-commerce cloud platform. The cosmetic demand attribute data of the cosmetic service user of the cosmetic e-commerce service terminal is obtained, and the cosmetic demand attribute data and the cosmetic demand attribute data corresponding to the cloud-end recommended cosmetic scheme are respectively subjected to cosmetic feature mining, and then the loss cosmetic feature between the two is calculated. Based on the preset machine learning mining network, the loss cosmetic feature is mined to obtain the supplementary demand attribute information corresponding to the cosmetic demand attribute data.

[0004] However, the existing technology still has deficiencies in analyzing the needs of users, and cannot select and recommend cosmetics according to the needs of users, so that the recommendation of cosmetics lacks refinement. SUMMARY

[0005] Therefore, the present application provides a market auxiliary decision-making system based on big data, which can solve the problem of insufficient refinement of related product recommendation.

[0006] To achieve the above purpose, the present application provides a market auxiliary decision-making system based on big data, which comprises:

[0007] A receiving terminal is used to receive the cataloging mark information of the current terminal and the state parameter information of the page window of the current terminal. The state parameter information of the page window includes the URL address of the webpage and the position information of the webpage scroll bar.

[0008] A processing module is connected with the receiving terminal, used to determine the perfection degree of the input items in the cataloging mark information, and determine the first recommendation list based on the current user according to the perfection degree of the input items in the cataloging mark information.

[0009] a storage module connected with the receiving terminal, configured to store and aggregate the state parameter information of at least one page window of the current terminal, aggregate as historical state parameter information, and store product database information on the current terminal;

[0010] an analysis module connected with the processing module and the storage module respectively, configured to determine a second recommendation list according to the historical state parameter information and the product database information, determine a target recommendation list according to the overlapping items of the first recommendation list and the second recommendation list, and feed back the target recommendation list to the receiving terminal as response information, wherein the target recommendation list includes at least one recommendation item, and the recommendation item matches the catalog mark of the current terminal and the historical state parameter information.

[0011] Further, the processing module includes an acquisition unit, a decoding unit, a determination unit and a comparison unit,

[0012] the acquisition unit is configured to acquire an entry in the catalog mark information of the receiving terminal, wherein the entry includes essential information and secondary information;

[0013] the decoding unit is configured to decode the essential information and the secondary information, and fuse the decoded data sequences of the essential information and the secondary information to form a fused data sequence;

[0014] the determination unit is configured to determine the perfection degree of the fused data sequence after decoding;

[0015] the comparison unit is configured to compare the perfection degree of the fused data sequence with a standard perfection degree to obtain a comparison result, and determine a first recommendation list based on the current user according to the comparison result.

[0016] Further, when the comparison unit compares the perfection degree of the data sequence with the standard perfection degree, the comparison includes adjusting a preset standard product recommendation amount L0, and a preset adjustment coefficient k is provided, wherein 1>k>0;

[0017] if the perfection degree of the decoded data sequence is greater than the standard perfection degree, the first adjustment coefficient is used to increase the preset standard product recommendation amount L0, and the first standard product recommendation amount in the first list after adjustment is L1=L0×(1+k);

[0018] if the perfection degree of the decoded data sequence belongs to the standard perfection degree, the standard product recommendation amount L0 is used for recommendation;

[0019] If the completeness of the decoded data sequence is less than the standard completeness, then a second adjustment coefficient is used to reduce the standard product recommendation quantity L0, and the second standard product recommendation quantity in the adjusted first list is L2=L0*(1-k).

[0020] Further, the analysis module comprises a statistical unit, a sorting unit, an extraction unit, a screening unit and a merging unit.

[0021] The statistical unit is configured to count the browsing frequency of the URL address of any webpage.

[0022] The sorting unit is configured to sort the product set list from high to low according to the browsing frequency.

[0023] The extraction unit is configured to extract keywords from the product name and the function of the product in the product set list.

[0024] The screening unit is configured to screen the product based on the extracted keywords in the product database information, so as to determine the second recommendation list based on the current user.

[0025] The merging unit is configured to determine the target recommendation list according to the coincident items of the first recommendation list and the second recommendation list, and feed back the target recommendation list to the receiving terminal as response information.

[0026] Further, when the screening unit screens the product based on the extracted keywords in the product database information, the screening unit identifies the keywords in the product database information and counts the number P1 of products to be recommended that meet the keyword identification.

[0027] If P1≤PM, the product screening is not needed, and the second recommendation list is generated.

[0028] If P1>PM, the difference between the two is calculated, the difference is determined as the filtering amount ΔP=P1-P0 of the product, and the products to be recommended are sorted from high to low according to the keyword coincidence degree, and the products with low keyword coincidence degree are filtered in sequence according to the difference, so as to form the second recommendation list.

[0029] Wherein, PM represents the maximum recommendation quantity of the product in the second recommendation list.

[0030] Further, when the merging unit determines the target recommendation list according to the coincident items of the first recommendation list and the second recommendation list, the merging unit identifies the coding features of the items in the first recommendation list and the second recommendation list, and extracts the same coding features as the actual recommended items in the target recommendation list.

[0031] Setting a standard recommendation item in a target recommendation list;

[0032] If the actual recommendation item in the target recommendation list is less than the standard recommendation item, a second recommendation list is supplemented based on the recommendation item and fed back to the receiving terminal as response information as a target recommendation list;

[0033] If the actual recommendation item in the target recommendation list is greater than or equal to the standard recommendation item, the actual recommendation item is fed back to the receiving terminal as response information as a target recommendation list.

[0034] Further, the decoding unit is pre-set with decoding data of key information, including essential information decoding data and secondary information decoding data, the key information in the entry transmitted by the receiving terminal is decoded, and the decoded data of the essential information and the secondary information is fused.

[0035] Further, when the decoded data of the essential information and the secondary information is fused, different data types of the secondary information are inserted into the data sequence of the essential information, and the position in the data sequence of the essential information is determined.

[0036] Further, the first data type and the second data type are pre-set, the first data type is feedback data, and the second data type is supplementary data;

[0037] If the secondary data is of the first data type, the secondary data is inserted into the first third position in the data sequence of the essential information for priority reception;

[0038] If the secondary data is of the second data type, the secondary data is inserted into the corresponding supplementary position in the data sequence of the essential information for integrated reception.

[0039] Further, the receiving terminal includes an input module, an authentication module and a cloud module;

[0040] The input module is used to obtain the catalog mark information of the current terminal and the state parameter information of the page window of the current terminal, and the catalog mark information includes age, gender, skin type, skin sensitivity, daily water intake and regional information;

[0041] The authentication module is connected with the input module and is used to authenticate the catalog mark information;

[0042] The cloud module is connected with the input module and the authentication module and is used to upload the browsing frequency data and the catalog mark information.

[0043] Compared with the prior art, the beneficial effects of the present application are that, by means of the catalog mark information of the current terminal and the state parameter information of the page window of the current terminal, the determination of the product recommendation list is carried out in the processing module and the analysis module respectively, the screening and recommendation of products are realized according to the characteristics of the catalog mark information and the potential demand embodied by the catalog mark information, so that the screening and recommendation of products can be refined to facilitate targeted selection. The target recommendation list is determined by overlapping the first recommendation list and the second recommendation list, and the target recommendation list is fed back to the receiving terminal as response information, which realizes the integration of the recommendation information and increases the recommendation accuracy. The data sequence of the secondary information and the essential information is arranged by fusing the decoded data of the essential information and the secondary information, the order of the data is accepted and fused by the arrangement of the data sequence of the secondary information and the essential information, and the overall efficiency of the market auxiliary decision-making system based on big data is improved.

[0044] Especially, the catalog mark information is received by the acquisition unit, the decoded data sequence of the essential information and the secondary information is fused by the decoding unit, the perfection degree of the fused data sequence after decoding is determined by the determination unit, and the first recommendation list is determined by comparing the perfection degree of the fused data sequence with the standard perfection degree by the comparison unit.

[0045] Especially, the real-time adjustment of the product recommendation quantity in the first list is realized by comparing the perfection degree of the data sequence with the standard perfection degree by the comparison unit, the corresponding recommendation quantity is determined according to the completeness of the information entry, so that the completeness and the quantity and accuracy of the recommendation are positively correlated, the purpose of targeted product recommendation is realized, and the efficiency of auxiliary decision-making is improved.

[0046] Especially, the browsing frequency of the URL address of any webpage is counted by the statistical unit, the browsing frequency is sorted from high to low by the sorting unit, the keywords of the product name and the function of the product in the product set list are extracted by the extraction unit, the products in the product database information are screened based on the extracted keywords by the screening unit, the overlapping items of the first recommendation list and the second recommendation list are merged by the merging unit, and the target recommendation list is determined, so that the product list recommended is more accurate.

[0047] Especially, by identifying the keywords in the product database information, the information in the database is selectively screened, so that the data recommendation quantity is reduced after screening, the data processing efficiency is improved, and the product recommendation quantity in the final output second recommendation list is simplified.

[0048] Especially, the identification of the coding features of the items in the first recommendation list and the second recommendation list, the extraction of the same coding features as actual recommended items in the target recommendation list, realizes the integration of the recommended information, so that the auxiliary decision system can balance the accuracy of data processing and the appropriateness of information volume, improves the processing efficiency of information processing, and increases the matching degree of recommendation.

[0049] Especially, by fusing the decoded data of the essential information and the secondary information in the decoding unit, the processing module selectively receives information, and if the decoded essential information and the secondary information contain decoding data related to key information, the receiving and fusing are performed, realizing further extraction of the information and avoiding missing of received information. Especially, by inserting different data types of the secondary information into the data sequence of the essential information, and highly matching the different data types of the secondary information with the receiving position of the data sequence of the essential information, the comprehensiveness of information receiving is realized.

[0050] Especially, by fusing the decoded data of the essential information and the secondary information, the arrangement of the data sequence of the secondary information and the essential information is realized, and through the arrangement of the data sequence of the secondary information and the essential information, the sequential receiving and fusing of the data are realized, improving the overall efficiency of the market auxiliary decision system based on big data.

[0051] Especially, through the input module, the acquisition of the cataloging mark information is realized, so that the processing module and the analysis module can provide subsequent recommendation services. Through the authentication function of the authentication module, the secondary confirmation of the cataloging mark information by the user is realized, ensuring the accuracy of the information. Through the cloud module, the browsing information and the reconfirmed cataloging mark information are transmitted to the processing module, realizing the storage and backup of the information. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 The structure schematic diagram of the market auxiliary decision system based on big data is provided for the embodiments of the application. DETAILED DESCRIPTION

[0053] In order to make the purpose and advantages of the application more clear and understandable, the application will be further described below in combination with embodiments; it should be understood that the specific embodiments described herein are only used to explain the application, and do not limit the application.

[0054] The preferred embodiments of the application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the application, and are not intended to limit the protection scope of the application.

[0055] It should be noted that in the description of the present application, the terms of direction or positional relationship indicated by "upper", "lower", "left", "right", "inner", "outer" and the like are based on the direction or positional relationship shown in the drawings, which is merely for the convenience of description, and does not indicate or imply that the device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application.

[0056] In addition, it should be noted that in the description of the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting" should be understood in a broad sense, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0057] Please refer to Figure 1 The market assisted decision-making system based on big data provided by the embodiment of the present application comprises:

[0058] The receiving terminal 10 is used to receive the catalog mark information of the current terminal and the state parameter information of the page window of the current terminal;

[0059] The processing module 20 is connected with the receiving terminal, and is used to determine the perfection degree of the entry in the catalog mark information, and determine the first recommended list based on the current user according to the perfection degree of the entry in the catalog mark information;

[0060] The storage module 30 is connected with the receiving terminal, and is used to store and aggregate the browsing data information of the user on at least one terminal website, aggregate as historical state parameter information, and store the product database information on the terminal website;

[0061] The analysis module 40 is connected with the processing module and the storage module respectively, and determines the second recommended list according to the historical state parameter information and the product database information, determines the target recommended list according to the overlapping items of the first recommended list and the second recommended list, and feeds back the target recommended list to the receiving terminal as response information, the target recommended list at least includes one recommended item, and the recommended item matches the catalog mark of the current terminal and the historical state parameter information.

[0062] Specifically, any of the web pages contains relevant product information, and the URL address of the web page corresponds to the product information one by one.

[0063] Specifically, in the embodiment of the application, the product recommendation list is determined in the processing module and the analysis module through the catalog mark information of the current terminal and the state parameter information of the page window of the current terminal, the product is screened and recommended according to the characteristics of the catalog mark information and the potential demand embodied by the catalog mark information, so that the product can be finely screened and recommended to provide targeted selection. The target recommendation list is determined by overlapping the first recommendation list and the second recommendation list, and the target recommendation list is fed back to the receiving terminal as response information, which realizes the integration of the recommendation information and increases the recommendation accuracy. The data sequences of the secondary information and the essential information are arranged by fusing the decoded data of the essential information and the secondary information, the order of the data is accepted and fused through the arrangement of the data sequences of the secondary information and the essential information, and the overall efficiency of the market auxiliary decision system based on big data is improved.

[0064] Specifically, the processing module comprises an acquisition unit 201, a decoding unit 202, a determination unit 203 and a comparison unit 204,

[0065] The acquisition unit 201 is used to acquire the entry in the catalog mark information of the receiving terminal, and the entry comprises essential information and secondary information;

[0066] The decoding unit 202 is used to decode the essential information and the secondary information, fuse the decoded data sequences of the essential information and the secondary information, and form a fused data sequence;

[0067] The determination unit 203 is used to determine the perfection degree of the fused data sequence after decoding;

[0068] The comparison unit 204 is used to compare the perfection degree of the fused data sequence with a standard perfection degree to obtain a comparison result, and determine a first recommendation list based on the current user according to the comparison result.

[0069] Specifically, in the embodiment of the application, the acquisition unit realizes the reception of the entry in the catalog mark information, the decoding unit realizes the fusion of the decoded data sequences of the essential information and the secondary information, the determination unit determines the perfection degree of the fused data sequence after decoding, and the comparison unit compares the perfection degree of the fused data sequence with the standard perfection degree to achieve the purpose of determining the first recommendation list based on the current user.

[0070] Specifically, when the comparison unit compares the perfection degree of the data sequence with the standard perfection degree, the following steps are included: adjusting the preset standard product recommendation amount L0, and pre-setting an adjustment coefficient k, wherein 1>k>0.

[0071] If the completeness of the decoded data sequence is greater than the standard completeness, the first adjustment coefficient is used to increase the preset standard product recommendation quantity L0, and the product recommendation quantity of the first standard in the first list after adjustment is L1=L0x(1+k);

[0072] If the completeness of the decoded data sequence belongs to the standard completeness, the standard product recommendation quantity L0 is used for recommendation;

[0073] If the completeness of the decoded data sequence is less than the standard completeness, the second adjustment coefficient is used to decrease the standard product recommendation quantity L0, and the product recommendation quantity of the second standard in the first list after adjustment is L2=L0x(1-k).

[0074] Specifically, in the embodiment of the application, the comparison unit compares the completeness of the data sequence with the standard completeness, so that the real-time adjustment of the product recommendation quantity in the first list is realized, the size of the recommendation quantity is determined according to the completeness of the information entry, the completeness and the size and accuracy of the recommendation are positively correlated, the purpose of targeted product recommendation is achieved, and the efficiency of auxiliary decision-making is improved.

[0075] Specifically, the analysis module includes a statistical unit 401, a sorting unit 402, an extraction unit 403, a screening unit 404 and a merging unit 405.

[0076] The statistical unit 401 is configured to count the browsing frequency of the URL address of any webpage.

[0077] The sorting unit 402 is configured to sort the product set list from high to low according to the browsing frequency.

[0078] The extraction unit 403 is configured to extract the keywords of the product name and the function of the product in the product set list.

[0079] The screening unit 404 is configured to screen the product in the product database information based on the extracted keywords, and determine the second recommendation list based on the current user.

[0080] The merging unit 405 is configured to determine the target recommendation list according to the coincident items of the first recommendation list and the second recommendation list, and feed back the target recommendation list to the receiving terminal as response information.

[0081] Specifically, in the embodiment of the present application, the statistical unit realizes the statistics of the browsing frequency of the URL address of any webpage, the sorting unit realizes the sorting from high to low of the browsing frequency, the extraction unit realizes the extraction of the keywords of the product name and the function of the product in the product set list, the screening unit realizes the screening of the product in the product database information based on the extracted keywords, the merging unit realizes the merging of the coincident items of the first recommended list and the second recommended list, and determines the target recommended list, so that the recommended product list is more accurate.

[0082] Specifically, when the screening unit screens the product in the product database information based on the extracted keywords, the keyword recognition is performed in the product database information, and the number P1 of products to be recommended that meet the keyword recognition is counted,

[0083] If P1≤PM, the product screening is not needed, and the second recommended list is generated;

[0084] If P1>PM, the difference value is calculated, the difference value is determined as the filtering amount ΔP=P1-P0 of the product, the products to be recommended are sorted from high to low according to the keyword coincidence degree, and the products with low keyword coincidence degree are filtered in sequence according to the difference value, so as to form the second recommended list;

[0085] PM represents the maximum recommended number of products in the second recommended list.

[0086] Specifically, in the embodiment of the present application, the keyword recognition is performed in the product database information, so that the information in the database is selectively screened, thereby realizing the reduction of the data recommendation amount after screening, improving the data processing efficiency, and further realizing the simplification of the product recommendation amount in the finally output second recommended list.

[0087] Specifically, when the target recommended list is determined according to the coincident items of the first recommended list and the second recommended list, the merging unit identifies the coding features of the items in the first recommended list and the second recommended list, and extracts the same coding features as the actual recommended items in the target recommended list;

[0088] The standard recommended items in the target recommended list are set;

[0089] If the actual recommended items in the target recommended list are less than the standard recommended items, the second recommended list is supplemented as the target recommended list based on the recommended items and fed back to the receiving terminal as response information;

[0090] If the actual recommendation items in the target recommendation list are greater than or equal to the standard recommendation items, the actual recommendation items are fed back to the receiving terminal as the target recommendation list as the response information.

[0091] Specifically, in the embodiment of the present application, the items in the first recommendation list and the second recommendation list are identified by encoding features, and the same encoding features are extracted and merged as actual recommendation items in the target recommendation list, so that the recommendation information is integrated for the recommendation purpose, the auxiliary decision system can take into account the accuracy of data processing and the appropriateness of information volume, the processing efficiency of information processing is improved, and the matching degree of recommendation is increased.

[0092] Specifically, the decoding data of the key information is pre-set in the decoding unit, the decoding data of the key information includes necessary information decoding data and secondary information decoding data, the key information contained in the input item transmitted by the receiving terminal is decoded, and the decoded data of the necessary information and the secondary information is fused.

[0093] Specifically, in the embodiment of the present application, the decoded data of the necessary information and the secondary information is fused in the decoding unit, so that the processing module selectively receives information, if the decoded necessary information and the secondary information contain the decoding data of the key information, the receiving and fusion are performed, the further extraction of the information is realized, and the loss of received information is avoided.

[0094] Specifically, when the decoded data of the necessary information and the secondary information is fused, the different data types of the secondary information are inserted into the data sequence of the necessary information, and the position of the secondary information in the data sequence of the necessary information is determined.

[0095] Specifically, in the embodiment of the present application, the different data types of the secondary information are inserted into the data sequence of the necessary information, and the different data types of the secondary information are highly matched with the receiving position of the data sequence of the necessary information, so that the comprehensiveness of information receiving is realized.

[0096] Specifically, the position of the secondary information in the data sequence of the necessary information is determined according to the data type of the decoded secondary information.

[0097] The first data type and the second data type are pre-set, the first data type is feedback data, and the second data type is supplementary data.

[0098] If the secondary data is the first data type, the secondary data is inserted into the first third position of the data sequence of the necessary information for priority receiving.

[0099] If the secondary data is of the second data type, then the secondary data is inserted into the corresponding supplementary position in the data sequence of the essential information for integrated reception.

[0100] Specifically, the feedback data is the user's experience of using the relevant product, evaluation score, season of use, and way of use, and the experience includes whether the skin is functionally affected and whether it will be repurchased.

[0101] Specifically, in the embodiment of the application, the arrangement of the data sequence of the secondary information and the essential information is realized by fusing the decoded data of the essential information and the secondary information, and the sequential reception and fusion of the data are realized through the arrangement of the data sequence of the secondary information and the essential information, thereby improving the overall efficiency of the market auxiliary decision-making system based on big data.

[0102] Specifically, the receiving terminal comprises an input module 101, an authentication module 102, and a cloud module 103.

[0103] The input module 101 is used to obtain the catalog mark information of the current terminal and the state parameter information of the page window of the current terminal, and the catalog mark information includes age, gender, skin type, skin sensitivity, daily water intake, and regional information.

[0104] The authentication module 102 is connected with the input module 101 and is used to authenticate the catalog mark information.

[0105] The cloud module 103 is connected with the input module 101 and the authentication module 102 and is used to upload the browsing frequency data and the catalog mark information.

[0106] Specifically, in the embodiment of the application, the input module is used to obtain the catalog mark information, so as to facilitate the subsequent recommendation service of the processing module and the analysis module. The authentication function of the authentication module realizes the secondary confirmation of the catalog mark information by the user, thereby ensuring the accuracy of the information. The cloud module transmits the browsing information and the reconfirmed catalog mark information to the processing module, thereby realizing the storage and backup of the information.

[0107] So far, the technical solutions of the present application have been described in combination with the preferred embodiments shown in the drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after the changes or replacements will all fall within the protection scope of the present application.

[0108] The above only describes the preferred embodiments of the present application and is not intended to limit the present application; the present application can have various changes and variations for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A market-supported decision-making system based on big data, characterized in that, include: A receiving terminal is used to receive the current terminal's recording mark information and the current terminal's page window status parameter information, wherein the page window status parameter information includes the webpage's URL address and the webpage scroll bar's position information; The processing module, connected to the receiving terminal, is used to determine the completeness of the bibliographic marker information and to determine a first recommendation list based on the current user according to the completeness of the entries in the bibliographic marker information. A storage module, connected to the receiving terminal, is used to store and summarize the status parameter information of at least one page window of the current terminal, summarize it into historical status parameter information, and store the product database information on the current terminal; The analysis module is connected to the processing module and the storage module respectively. It determines a second recommendation list based on the historical status parameter information and the product database information, and determines a target recommendation list based on the overlapping items of the first recommendation list and the second recommendation list. The target recommendation list is fed back to the receiving terminal as response information. The target recommendation list includes at least one recommendation item, and the recommendation item matches the current terminal's recording mark information and the historical status parameter information. The processing module includes: an acquisition unit, a decoding unit, a determination unit, and a comparison unit. The acquisition unit is used to acquire the input items in the recording mark information of the receiving terminal, and the input items include necessary information and secondary information; The decoding unit is used to decode the necessary information and the secondary information, and to fuse the decoded data sequences of the necessary information and the secondary information to form a fused data sequence; The determining unit is used to determine the completeness of the decoded fused data sequence; The comparison unit is used to compare the completeness of the fused data sequence with the standard completeness to obtain the comparison result, and to determine the first recommendation list based on the current user based on the comparison result. When the comparison unit compares the data sequence with the standard completeness, it includes: adjusting the preset standard product recommendation quantity L0, and setting an adjustment coefficient k in advance, where 1>k>0; If the completeness of the decoded data sequence is greater than the completeness of the standard, the first adjustment coefficient is used to increase the recommended quantity L0 of the preset standard product. The recommended quantity of the first standard product in the first list after adjustment is L1 = L0 × (1 + k). If the completeness of the decoded data sequence is within the standard completeness range, then the standard product recommendation quantity L0 will be used for recommendation. If the completeness of the decoded data sequence is less than the standard completeness, the standard product recommendation quantity L0 is reduced by the second adjustment coefficient. The product recommendation quantity of the second standard in the first list after adjustment is L2 = L0 × (1-k). The analysis module includes a statistical unit, a sorting unit, an extraction unit, a filtering unit, and a merging unit; The statistical unit is used to count the browsing frequency of any webpage's URL address; The sorting unit is used to sort the products from high to low according to the browsing frequency to obtain a product set list; The extraction unit is used to extract keywords from the product names and functions of the product set list; The filtering unit is used to filter products in the product database information based on the extracted keywords, in order to determine a second recommendation list based on the current user; The merging unit is used to determine a target recommendation list based on the overlapping items of the first recommendation list and the second recommendation list, and to feed back the target recommendation list to the receiving terminal as response information; When the filtering unit filters products in the product database information based on the extracted keywords, it identifies the keywords in the product database information and counts the number P1 of products that match the identified keywords. If P1≤PM, then there is no need to filter products and a second recommendation list is generated. If P1>PM, calculate the difference between the two, and determine the product filtering quantity ΔP=P1-P0 based on the difference. Then, sort the products with high to low keyword overlap according to the number of products to be recommended, and filter them sequentially from products with low keyword overlap according to the difference to form a second recommendation list. Here, PM represents the maximum number of recommendations for a product in the second recommendation list.

2. The market auxiliary decision-making system based on big data according to claim 1, characterized in that, When determining the target recommendation list based on the overlapping items in the first recommendation list and the second recommendation list, the merging unit identifies the encoding features of the items in the first recommendation list and the second recommendation list, and merges and extracts the same encoding features as the actual recommended items in the target recommendation list; Set the standard recommended items in the target recommendation list; If the actual recommended items in the target recommendation list are less than the standard recommended items, a second recommendation list is added based on the recommended items to form the target recommendation list and fed back to the receiving terminal as response information. If the actual recommended items in the target recommendation list are greater than or equal to the standard recommended items, then the actual recommended items are fed back to the receiving terminal as response information as part of the target recommendation list.

3. The market auxiliary decision-making system based on big data according to claim 2, characterized in that, The decoding unit is pre-set with key information decoding data, which includes essential information decoding data and secondary information decoding data. The key information contained in the input item transmitted by the receiving terminal is decoded, and the data after decoding the essential information and the secondary information are merged.

4. The market auxiliary decision-making system based on big data according to claim 3, characterized in that, When fusing the data after decoding the necessary information and the secondary information, different data types of the secondary information are inserted into the data sequence of the necessary information, and their positions in the necessary information data sequence are determined.

5. The market-supported decision-making system based on big data according to claim 4, characterized in that, Determining the position of the data type within the necessary information data sequence based on the decoded secondary information includes: A first data type and a second data type are preset, where the first data type is feedback data and the second data type is supplementary data; If the secondary data is of the primary data type, then the secondary data is inserted into the first third of the data sequence of the necessary information for priority reception. If the secondary data is of the second data type, then the secondary data is inserted into the corresponding supplementary position in the data sequence of the necessary information for integration and reception.

6. The market auxiliary decision-making system based on big data according to claim 5, characterized in that, The receiving terminal includes: an input module, an authentication module, and a cloud module; The input module is used to accept the current terminal's recording mark information and the current terminal's page window status parameter information. The recording mark information includes: age, gender, skin type, skin sensitivity, daily water intake, and regional information. The authentication module is connected to the input module and is used to authenticate the recording mark information; The cloud module is connected to the input module and the authentication module to upload the status parameter information of the page window and the recording mark information.

Images