Commodity list content richness evaluation method and device, storage medium and equipment

Abstract

The commodity list content richness evaluation method, device, storage medium and equipment provided by the application can obtain the requested commodity list when at least one test user uses a unified search term to search in a test process when evaluating the commodity list content richness of a to-be-tested system. Since the commodity list contains a plurality of commodity pits, and different commodity pits at different positions display different commodity information, the application can count the commodity features of the commodity information displayed by the commodity pits at different positions in at least one commodity list according to a preset statistical dimension, and then determine the feature number of all commodity features in at least one commodity list and the feature weight of each commodity feature in the commodity pits at all positions. In this way, the content richness of the commodity list can be evaluated. This process does not require manual positioning and investigation, effectively improves the evaluation efficiency, and reduces the labor cost.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to a method, apparatus, storage medium, and computer equipment for evaluating the richness of product list content. Background Technology

[0002] With the continuous development of the e-commerce industry, the scenarios for product recommendations when users search for goods on e-commerce platforms are becoming increasingly diverse. For example, when a user searches for related products, the e-commerce platform displays a list of relevant products based on the user's search keywords. Different product slots in the list display corresponding product information, including brand, category, tags, price, and target audience. Therefore, the richer the product information displayed in the list, the more attractive it is to users, thus helping to improve the user retention rate of the e-commerce platform.

[0003] Currently, the assessment of the richness of product listing content is mainly based on manual checks. For example, when a supplier reports a decline in the search experience related to a particular brand, technicians reproduce the production issue for abnormal users and then investigate and resolve the problem. However, this method of assessment cannot accurately determine whether the reported problem is an isolated case or a widespread phenomenon, thus failing to assess the severity of the problem. This leads to higher subsequent maintenance costs, and the use of manual investigation and location also results in higher labor costs. Summary of the Invention

[0004] The purpose of this application is to at least address one of the aforementioned technical deficiencies, particularly the existing methods for assessing the richness of product list content, which cannot accurately determine whether the reported problem is an isolated case or a widespread phenomenon, thus failing to assess the severity of the problem and resulting in high subsequent maintenance costs. Furthermore, the use of manual investigation and location also leads to high labor costs.

[0005] This application provides a method for evaluating the richness of product list content, the method comprising:

[0006] When testing the richness of the product list content of the system under test, at least one test user requests a product list for the same search term. The product list contains multiple product slots, and different product slots at different positions display different product information. When multiple test users request multiple product lists, the product information displayed in the same position of the product slots in different product lists is different.

[0007] According to a preset statistical dimension, the product features of the product information displayed in product slots at different positions in at least one of the product lists are statistically analyzed to determine the number of features of the product features statistically analyzed under the statistical dimension for the product information displayed in product slots at all positions in at least one of the product lists, and the feature weight of each product feature in product slots at all positions in at least one of the product lists.

[0008] The richness of the product list content of the system under test is evaluated based on the number of features of the product features displayed in the product slots at all positions in at least one of the product lists under the statistical dimension, and the feature weight of each product feature in the product slots at all positions in at least one of the product lists.

[0009] Optionally, the step of statistically analyzing the product features of product information displayed in product slots at different positions in at least one of the product lists according to a preset statistical dimension, and determining the number of features of product features statistically analyzed under the statistical dimension for product information displayed in product slots at all positions in at least one of the product lists, includes:

[0010] When there is only one product list, the product features of the product information displayed in the product slots at different positions in the product list are statistically analyzed according to a preset statistical dimension to obtain a first statistical result. Duplicate product features in the first statistical result are removed, and the number of product features of the product information displayed in the product slots at all positions in the product list under the statistical dimension is determined based on the removed first statistical result.

[0011] When there are multiple product lists, the product features of the product information displayed in different positions in each product list are statistically analyzed according to a preset statistical dimension to obtain a second statistical result. Duplicate product features in the second statistical result are removed, and the number of product features of the product information displayed in all positions in all product lists under the statistical dimension is determined based on the removed second statistical result.

[0012] Optionally, the exposure weight of product slots at different positions in the same product list is different, while the exposure weight of product slots at the same position in different product lists is the same.

[0013] The step involves statistically analyzing the product features of product information displayed in product slots at different locations in at least one of the product lists according to a preset statistical dimension, and determining the feature weight of each product feature in all product slots at at least one location in the product list, including:

[0014] According to the preset statistical dimensions, the product features of the product information displayed in the product slots at different positions in at least one of the product lists are statistically analyzed to obtain multiple product features;

[0015] For each product feature:

[0016] Count the number of product lists corresponding to the product feature in product slots at different positions in at least one of the product lists, and obtain the number of users corresponding to the product feature in each product slot, wherein each test user corresponds to one product list;

[0017] Based on the exposure weight of the product slots at each location, the number of users corresponding to the product feature in each product slot, and the total number of test users, calculate the feature weight of the product feature in all product slots at at least one location in the product list.

[0018] Optionally, the exposure weight of product slots at different locations in the same product list is set based on the probability that the product information in the product slot is exposed, and the exposure weight of the product slot is positively correlated with the probability that the product information in the product slot is exposed.

[0019] Optionally, the evaluation of the richness of the product list content of the system under test under the statistical dimension, based on the number of features of the product features displayed in the product slots at all positions in at least one of the product lists and the feature weight of each product feature in the product slots at all positions in at least one of the product lists, includes:

[0020] If the number of features of the product information displayed in the product slots at all positions in at least one of the product lists under the statistical dimension exceeds a preset feature number threshold, and the weight difference of the feature weights of each product feature in the product slots at all positions in at least one of the product lists does not exceed a preset weight difference threshold, then the richness of the product list content of the system under test under the statistical dimension is higher than a preset richness threshold.

[0021] If the number of features of the product information displayed in all positions of the product list under the statistical dimension does not exceed a preset feature number threshold, and the weight difference of the feature weights of each product feature in all positions of the product list exceeds a preset weight difference threshold, then the richness of the product list content of the system under test under the statistical dimension is lower than a preset richness threshold.

[0022] Optionally, when testing the richness of the product list content of the system under test, before obtaining the product list requested by at least one test user for the same search term, the process further includes:

[0023] Configure the settings for testing the richness of the product list content in the system under test;

[0024] The configuration information includes the search terms set for the product list to be tested, the simulated test users when requesting the product list to be tested, the number of test users, and the statistical dimensions used to evaluate the richness of the content of the product list to be tested.

[0025] Optionally, the method further includes:

[0026] The evaluation results are stored in a database, and an evaluation report corresponding to the evaluation results is generated in the database.

[0027] This application also provides a device for evaluating the richness of product list content, including:

[0028] The data acquisition module is used to acquire the product list requested by at least one test user for the same search term when testing the richness of the product list content of the system under test. The product list contains multiple product slots, and the product slots at different positions display different product information. When multiple test users request multiple product lists, the product information displayed in the same position of the product slots in different product lists is different.

[0029] The data statistics module is used to statistically analyze the product features of the product information displayed in product slots at different positions in at least one of the product lists according to a preset statistical dimension, and to determine the number of features of the product features of the product information displayed in product slots at all positions in at least one of the product lists under the statistical dimension, as well as the feature weight of each product feature in product slots at all positions in at least one of the product lists.

[0030] The richness assessment module is used to assess the richness of the product list content of the system under test under the statistical dimension based on the number of features of the product features displayed in the product slots at all positions in at least one of the product lists, and the feature weight of each product feature in the product slots at all positions in at least one of the product lists.

[0031] This application also provides a storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the product list content richness evaluation method as described in any of the above embodiments.

[0032] This application also provides a computer device, including: one or more processors, and memory;

[0033] The memory stores computer-readable instructions, which, when executed by the one or more processors, perform the steps of the product list content richness evaluation method as described in any of the above embodiments.

[0034] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0035] The product list content richness evaluation method, apparatus, storage medium, and device provided in this application can, when evaluating the product list content richness of the system under test, first obtain the product list requested by at least one test user using a unified search term during the test. This allows for both targeted screening of specific users and evaluation of product list content richness through random testing, reducing production issues and effectively lowering subsequent maintenance costs. Furthermore, since the product list contains multiple product slots, and different product slots display different product information, to evaluate the content richness of the product list, corresponding statistical dimensions can be pre-set. The product features of the product information displayed in different product slots at least one position in the product list can be statistically analyzed according to these statistical dimensions. This determines the feature count of all product features in at least one product list, as well as the feature weight of each product feature in all product slots. Thus, the content richness of the product list can be evaluated based on the feature count of all product features and the feature weight of each product feature, eliminating the need for manual location and screening, effectively improving evaluation efficiency while reducing labor costs. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 A flowchart illustrating a method for evaluating the richness of product list content provided in an embodiment of this application;

[0038] Figure 2 A page display diagram of the configuration page provided in the embodiments of this application;

[0039] Figure 3A schematic diagram of the structure of a product list content richness evaluation device provided in an embodiment of this application;

[0040] Figure 4 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0041] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0042] Currently, the assessment of the richness of product listing content is mainly based on manual checks. For example, when a supplier reports a decline in the search experience related to a particular brand, technicians reproduce the production issue for abnormal users and then investigate and resolve the problem. However, this method of assessment cannot accurately determine whether the reported problem is an isolated case or a widespread phenomenon, thus failing to assess the severity of the problem. This leads to higher subsequent maintenance costs, and the use of manual investigation and location also results in higher labor costs.

[0043] Based on this, this application proposes the following technical solution, as detailed below:

[0044] In one embodiment, such as Figure 1 As shown, Figure 1 This application provides a flowchart illustrating a method for evaluating the richness of product list content, as shown in the embodiments of this application. The application provides a method for evaluating the richness of product list content, which may include:

[0045] S110: When testing the richness of the product list content of the system under test, at least one test user requests a product list for the same search term.

[0046] In this step, when testing the richness of the product list content of the system under test, relevant statistical tasks can be pre-configured, such as configuring statistical dimensions, statistical scenarios, statistical users, and search terms. This allows the richness of the product list content of the system under test to be tested based on these statistical tasks, and to obtain the product list requested by at least one test user for the same search term.

[0047] Here, "system under test" refers to the merchant system on the e-commerce platform that allows users to search, browse, and purchase; "statistical dimension" refers to the dimensions corresponding to the product characteristics of the product information displayed in different positions of the product list, including but not limited to brand dimension, category dimension, and tag dimension; "statistical scenario" refers to the application scenario corresponding to the product list, such as search product list, brand product list, etc.; "statistical user" refers to the test user when testing the richness of the product list content of the system under test. This test user can be a designated single user or multiple random users, depending on the actual situation, and there are no restrictions here; "search term" refers to the keywords entered by the test user when requesting the product list in the system under test, such as dress, shirt, trousers, etc.

[0048] Once this application is configured as a statistics task, the richness of the product list content in the system under test can be tested. During the test, the system can retrieve the product list requested by test users for pre-defined search terms. Generally, the product list contains multiple product slots, with different product information displayed in different slots. This provides users with multiple choices and improves the user experience.

[0049] It is understandable that this application can designate a single user as a test user, or randomly simulate multiple users as test users. Different test users have different user accounts. When different user accounts log in to the system under test and perform searches, due to differences in browsing history, categories of interest, and consumption habits, the product information displayed in the same position in the product list returned by different user accounts will be somewhat different.

[0050] Furthermore, since there are many product slots in the product list, and the top 100 products in most product lists have a large exposure share, this application can count the product information displayed in the top 100 product slots of each product list. Of course, in actual application, it can also be set according to the actual situation, and there are no restrictions here.

[0051] S120: According to the preset statistical dimensions, statistically analyze the product features of the product information displayed in product slots at different positions in at least one product list, determine the number of product features of the product information displayed in product slots at all positions in at least one product list under the statistical dimensions, and the feature weight of each product feature in product slots at all positions in at least one product list.

[0052] In this step, when testing the richness of the product list content of the system under test by obtaining the product list through S110, after at least one test user requests the product list for the same search term, this application can statistically analyze the product features of the product information displayed in the product slots at different positions in the product list according to a preset statistical dimension. Based on the statistical results, the number of product features of the product information displayed in the product slots at all positions in all product lists under the statistical dimension is determined, as well as the feature weight of each product feature in the product slots at all positions in all product lists.

[0053] It should be noted that a statistical dimension can include one or more product features. For example, when the statistical dimension is brand, since different products may have the same or different brands, there will be multiple product features such as brand A, brand B, and brand C under this statistical dimension. Of course, the number of product features mainly depends on the search terms entered by the test user, the number of merchants connected to the system under test, and the product search function of the system under test.

[0054] In one specific implementation, when this application pre-sets a statistical dimension and ten test users, it can obtain ten product lists requested by the ten test users for the same search term, and statistically analyze the product features of the product information displayed in different positions of the ten product lists under the statistical dimension. For example, when the search term is "men's shoes" and the statistical dimension is the category dimension, the product features of the product information displayed in different positions of the ten product lists under the category dimension can be statistically analyzed, such as men's casual shoes, men's athletic shoes, men's business shoes, men's leather shoes, men's beach shoes, men's slippers, etc. After the statistics are completed, the number of product features of the product information displayed in all product slots of the ten product lists under the category dimension can be determined. For example, if the number of product features of the product information displayed in all product slots of the ten product lists under the category dimension is four, namely men's casual shoes, men's athletic shoes, men's leather shoes, and men's slippers.

[0055] Based on this, this application can further statistically analyze the product characteristics of the product information displayed in different positions of the ten product lists under the category dimension, and determine the feature weight of each product feature in all product slots across all product lists. For example, when statistically analyzing the category dimension, this application can count the number of test users whose "men's casual shoes" category appears in the first product slot of all product lists, the number of test users whose "men's casual shoes" category appears in the second product slot, the number of test users whose "men's casual shoes" category appears in the third...Nth product slot, and then calculate the feature weight of the product feature "men's casual shoes" in all product slots across all product lists based on the above statistical results.

[0056] Once the feature count of the product information displayed in all product slots of the ten product lists under the category dimension, and the feature weight of each product feature in all product slots of all product lists, can be determined, the richness of the product list content of the system under test can be evaluated under this statistical dimension.

[0057] S130: Based on the number of features of the product information displayed in the product slots at all positions in at least one of the product lists under the statistical dimension, and the feature weight of each product feature in the product slots at all positions in at least one product list, evaluate the richness of the product list content of the system under test under the statistical dimension.

[0058] In this step, after determining the number of features of the product information displayed in all positions of at least one product list under the statistical dimension, and the feature weight of each product feature in all positions of at least one product list through S120, the richness of the product list content of the system under test under the statistical dimension can be evaluated.

[0059] Specifically, when evaluating the richness of the product list content of the system under test under a preset statistical dimension, the more features of the product characteristics counted under that statistical dimension, the higher the richness of the product list content under that statistical dimension; conversely, the lower the richness of the product list content under that statistical dimension. When the feature weight of each product feature in all product slots is not significantly different, it indicates that the dispersion of the product list under that statistical dimension is high; conversely, it indicates that the dispersion of the product list under that statistical dimension is low.

[0060] In the above embodiments, when evaluating the richness of the product list content of the system under test, the product list requested by at least one test user using a unified search term during the test can be obtained first. This allows for screening of specific users and evaluation of the richness of the product list content through random testing, reducing production problems and effectively lowering subsequent maintenance costs. Furthermore, since the product list contains multiple product slots, and different product slots display different product information, to evaluate the richness of the product list content, corresponding statistical dimensions can be pre-set, and the product features of the product information displayed in different product slots at least one product list can be statistically analyzed according to these statistical dimensions. This determines the feature count of all product features in at least one product list, as well as the feature weight of each product feature in all product slots. In this way, the richness of the product list content can be evaluated based on the feature count of all product features and the feature weight of each product feature, eliminating the need for manual location screening, effectively improving evaluation efficiency while reducing labor costs.

[0061] In one embodiment, S120 involves statistically analyzing the product features of the product information displayed in at least one product slot at different locations in the product list according to a preset statistical dimension, and determining the number of features of the product features statistically analyzed under the statistical dimension for the product information displayed in at least one product slot at all locations in the product list. This may include:

[0062] S121: When there is only one product list, the product features of the product information displayed in the product slots at different positions in the product list are statistically analyzed according to a preset statistical dimension to obtain a first statistical result. Duplicate product features in the first statistical result are removed, and the number of product features statistically analyzed under the statistical dimension for the product information displayed in the product slots at all positions in the product list is determined based on the removed first statistical result.

[0063] S122: When there are multiple product lists, the product features of the product information displayed in different positions of each product list are statistically analyzed according to a preset statistical dimension to obtain a second statistical result. Duplicate product features in the second statistical result are removed, and the number of product features of the product information displayed in all positions of all product lists under the statistical dimension is determined based on the removed second statistical result.

[0064] In this embodiment, when statistically analyzing the product features of the product information displayed in the product slots at different positions in the product list under a preset statistical dimension, if there is only one product list, i.e., only one test user, the product features of the product information displayed in the product slots at different positions in the product list can be counted. Then, duplicate product features are removed, and the number of features of the remaining product features is counted.

[0065] If there are multiple product lists, it indicates that there are multiple test users. In this case, we can count the product features of the product information displayed in different positions in each product list. After collecting the product features counted in each product list, we can remove duplicate product features and count the number of features of the remaining product features.

[0066] In one embodiment, the exposure weight of product slots at different locations in the same product list is different, while the exposure weight of product slots at the same location in different product lists is the same.

[0067] In this embodiment, when calculating the feature weights of product features, the exposure weight of product slots at different positions in the product list can be considered, that is, the probability that the product slot is seen by the user. This makes the final feature weights of product features more consistent with the actual situation.

[0068] Furthermore, in this application, since users habitually browse products step by step from the top of the product list, the exposure weight of product slots at different positions in the same product list is different. However, the layout of product slots in different product lists is the same, so the exposure weight of product slots at the same position in different product lists is the same.

[0069] In S120, according to a preset statistical dimension, the product features of the product information displayed in product slots at different positions in at least one of the product lists are statistically analyzed to determine the feature weight of each product feature in all product slots at at least one position in the product list. This may include:

[0070] S201: According to the preset statistical dimensions, the product features of the product information displayed in the product slots at different positions in at least one of the product lists are statistically analyzed to obtain multiple product features.

[0071] S202: For each product feature: count the number of product lists corresponding to the product feature in product slots at different positions in at least one of the product lists, and obtain the number of users corresponding to the product feature in each product slot, wherein each test user corresponds to one product list.

[0072] S203: Based on the exposure weight of the product slots at each location, the number of users corresponding to the product feature in each product slot, and the total number of test users, calculate the feature weight of the product feature in all product slots at at least one of the product lists.

[0073] In this embodiment, when calculating the feature weights of product features, the number of product features displayed in each product slot in all product lists under a preset statistical dimension can be determined first. Then, for each product feature, the number of users corresponding to that product feature in different product slots can be counted. In this way, the feature weight of that product feature in all product slots in at least one product list can be calculated based on the exposure weight of each product slot, the number of users corresponding to that product feature in each product slot, and the total number of test users.

[0074] For example, the feature weight of product feature 1 in the product list = (exposure weight of product slot 1 * number of users corresponding to product feature 1 in product slot 1 + exposure weight of product slot 2 * number of users corresponding to product feature 1 in product slot 2 + ... + exposure weight of product slot N * number of users corresponding to product feature 1 in product slot N) / (exposure weight of product slot 1 * total number of test users + exposure weight of product slot 2 * total number of test users + ... + exposure weight of product slot N * total number of test users).

[0075] In one embodiment, the exposure weight of product slots at different locations in the same product list is set based on the probability that the product information in the product slot is exposed, and the exposure weight of the product slot is positively correlated with the probability that the product information in the product slot is exposed.

[0076] In this embodiment, since users habitually browse products from the top down of the product list, the exposure weight of product slots at different positions within the same product list varies. This exposure weight is primarily set based on the probability of the product information in that slot being exposed; the higher the probability of exposure, the higher the exposure weight of that slot, and vice versa. Normally, the exposure weight of the product slot from the first position to the last position in the product list will decrease sequentially.

[0077] In one embodiment, S130, evaluating the richness of the product list content of the system under test under the statistical dimension based on the number of features of the product features displayed in the product slots at all positions in at least one of the product lists, and the feature weight of each product feature in the product slots at all positions in at least one of the product lists, may include:

[0078] S131: If the number of features of the product information displayed in the product slots at all positions in at least one of the product lists under the statistical dimension exceeds a preset feature number threshold, and the weight difference of the feature weights of each product feature in the product slots at all positions in at least one of the product lists does not exceed a preset weight difference threshold, then the richness of the product list content of the system under test under the statistical dimension is higher than a preset richness threshold.

[0079] S132: If the number of features of the product information displayed in the product slots at all positions in at least one of the product lists does not exceed a preset feature number threshold, and the weight difference of the feature weights of each product feature in the product slots at all positions in at least one of the product lists exceeds a preset weight difference threshold, then the richness of the product list content of the system under test in the statistical dimension is lower than a preset richness threshold.

[0080] In this embodiment, when evaluating the richness of the product list content of the system under test under a preset statistical dimension, if the number of statistical product features exceeds a preset feature number threshold, and the weight difference between the feature weights of each product feature does not exceed a preset weight difference threshold, it indicates that the richness of the product list content of the system under test under that statistical dimension is higher than the preset richness threshold. That is, when there are many product features under the same statistical dimension and the weight difference between the feature weights of each product feature is not significant, the richness and dispersion of the product list content of the system under test under that statistical dimension are relatively high.

[0081] Correspondingly, if the number of features of the statistical product features does not exceed the preset feature number threshold, and the weight difference between the feature weights of each product feature exceeds the preset weight difference threshold, it indicates that the richness of the product list content of the system under test in this statistical dimension is lower than the preset richness threshold. That is, when there are few product features in the same statistical dimension and the weight difference between the feature weights of each product feature is large, the richness of the product list content of the system under test in this statistical dimension is low and the aggregation is high.

[0082] In one embodiment, when testing the richness of the product list content of the system under test in S110, before at least one test user requests a product list for the same search term, the process may further include:

[0083] S101: Configure the settings for testing the richness of the product list content of the system under test.

[0084] The configuration information includes the search terms set for the product list to be tested, the simulated test users when requesting the product list to be tested, the number of test users, and the statistical dimensions used to evaluate the richness of the content of the product list to be tested.

[0085] In this embodiment, as described above, when testing the richness of the product list content of the system under test, relevant statistical task items, i.e., configuration information, such as configuring statistical dimensions, statistical scenarios, test users, search terms, etc., can be pre-configured. This allows the richness of the product list content of the system under test to be tested based on these statistical task items, and the product list requested by at least one test user for the same search term to be obtained.

[0086] Indicatively, such as Figure 2 As shown, Figure 2 A page display diagram of the configuration page provided in the embodiments of this application; Figure 2 In the process of configuring statistical tasks, you can configure the statistical scenario, search terms, statistical dimensions, user types, number of random users, test domain, etc. Among them, user types can include specified users and random users. If you choose random users, you can also set the corresponding number of users in the number of random users field. After configuring the statistical task, you can click the "Start Execution" button to test and evaluate the richness of the product list content of the system under test.

[0087] In one embodiment, the method may further include:

[0088] S140: Store the evaluation results in the database and generate an evaluation report corresponding to the evaluation results in the database.

[0089] In this embodiment, after obtaining the evaluation results, the evaluation results can be saved to the database, and an evaluation report corresponding to the evaluation results can be generated in the database.

[0090] For example, the evaluation report generated by this application may include the currently configured statistical dimensions, such as brand dimension and category dimension, as well as the statistical scenario and the number of test users. When the statistical scenario is a brand landing page, the product features under the brand dimension may include the names of one or more different brands, and the product features under the category dimension may include one or more categories, such as men's casual shoes, men's shirts, and men's casual pants. For each product feature under each statistical dimension, statistics can be performed according to the product list content richness evaluation method of this application. This allows us to obtain the number of product features of product information in different positions in the product list under different statistical dimensions, as well as the number of users corresponding to each product feature in different positions. Through this evaluation report, we can clearly and intuitively understand the current product list content richness.

[0091] The following describes the evaluation of the richness of product list content provided in the embodiments of this application. The product list content richness evaluation device described below and the product list content richness evaluation method described above can be referred to in correspondence with each other.

[0092] In one embodiment, such as Figure 3 As shown, Figure 3 This application provides a schematic diagram of a product list content richness assessment device according to an embodiment of the present application; the present application also provides a product list content richness assessment device, which may include a data acquisition module 210, a data statistics module 220, and a richness assessment module 230, specifically including the following:

[0093] The data acquisition module 210 is used to acquire the product list requested by at least one test user for the same search term when testing the richness of the product list content of the system under test. The product list contains multiple product slots, and the product slots at different positions display different product information. When multiple test users request multiple product lists, the product information displayed in the same position of the product slots in different product lists is different.

[0094] The data statistics module 220 is used to statistically analyze the product features of the product information displayed in product slots at different positions in at least one of the product lists according to a preset statistical dimension, and to determine the number of features of the product features of the product information displayed in product slots at all positions in at least one of the product lists under the statistical dimension, as well as the feature weight of each product feature in product slots at all positions in at least one of the product lists.

[0095] The richness assessment module 230 is used to assess the richness of the product list content of the system under test under the statistical dimension based on the number of features of the product features displayed in the product slots at all positions in at least one of the product lists, and the feature weight of each product feature in the product slots at all positions in at least one of the product lists.

[0096] In the above embodiments, when evaluating the richness of the product list content of the system under test, the product list requested by at least one test user using a unified search term during the test can be obtained first. This allows for screening of specific users and evaluation of the richness of the product list content through random testing, reducing production problems and effectively lowering subsequent maintenance costs. Furthermore, since the product list contains multiple product slots, and different product slots display different product information, to evaluate the richness of the product list content, corresponding statistical dimensions can be pre-set, and the product features of the product information displayed in different product slots at least one product list can be statistically analyzed according to these statistical dimensions. This determines the feature count of all product features in at least one product list, as well as the feature weight of each product feature in all product slots. In this way, the richness of the product list content can be evaluated based on the feature count of all product features and the feature weight of each product feature, eliminating the need for manual location screening, effectively improving evaluation efficiency while reducing labor costs.

[0097] In one embodiment, the data statistics module 220 may include:

[0098] The first statistical module is used to, when the product list is one, statistically analyze the product features of the product information displayed in the product slots at different positions in the product list according to a preset statistical dimension, obtain a first statistical result, remove duplicate product features in the first statistical result, and determine the number of product features of the product information displayed in the product slots at all positions in the product list under the statistical dimension based on the removed first statistical result.

[0099] The second statistical module is used to perform statistical analysis on the product features of the product information displayed in different positions of each product list according to a preset statistical dimension when there are multiple product lists, to obtain a second statistical result, to remove duplicate product features in the second statistical result, and to determine the number of product features of the product information displayed in all positions of all product lists under the statistical dimension based on the removed second statistical result.

[0100] In one embodiment, the exposure weight of product slots at different locations in the same product list is different, while the exposure weight of product slots at the same location in different product lists is the same.

[0101] The data statistics module 220 may include:

[0102] The product feature statistics module is used to statistically analyze the product features of product information displayed in product slots at different locations in at least one of the product lists according to preset statistical dimensions, and obtain multiple product features.

[0103] The user count module is used to count the number of product lists corresponding to the product feature in product slots at different positions in at least one of the product lists for each product feature, and to obtain the number of users corresponding to the product feature in each product slot, wherein each test user corresponds to one product list.

[0104] The feature weight calculation module is used to calculate the feature weight of a product feature in all product slots in at least one of the product lists based on the exposure weight of the product slots at each location, the number of users corresponding to the product feature in each product slot, and the total number of test users.

[0105] In one embodiment, the richness assessment module 230 may include:

[0106] The first evaluation module is configured to determine if the number of features of the product information displayed in the product slots at all locations in at least one of the product lists under the statistical dimension exceeds a preset feature number threshold, and the weight difference of the feature weights of each product feature in the product slots at all locations in at least one of the product lists does not exceed a preset weight difference threshold, then the richness of the product list content of the system under test under the statistical dimension is higher than a preset richness threshold.

[0107] The second evaluation module is used to determine if the number of features of the product information displayed in the product slots at all locations in at least one of the product lists under the statistical dimension does not exceed a preset feature number threshold, and the weight difference of the feature weights of each product feature in the product slots at all locations in at least one of the product lists exceeds a preset weight difference threshold. In this case, the richness of the product list content of the system under test under the statistical dimension is lower than a preset richness threshold.

[0108] In one embodiment, the apparatus may further include:

[0109] The configuration information construction module is used to construct configuration information for testing the richness of the product list content of the system under test; wherein, the configuration information includes the search terms set for the product list to be tested, the simulated test users when requesting the product list to be tested, the number of test users, and the statistical dimensions for evaluating the richness of the product list content to be tested.

[0110] In one embodiment, the apparatus may further include:

[0111] The report generation module is used to store the evaluation results in the database and generate an evaluation report corresponding to the evaluation results in the database.

[0112] In one embodiment, this application also provides a storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the product list content richness evaluation method as described in any of the above embodiments.

[0113] In one embodiment, this application also provides a computer device, including: one or more processors, and memory.

[0114] The memory stores computer-readable instructions, which, when executed by the one or more processors, perform the steps of the product list content richness evaluation method as described in any of the above embodiments.

[0115] Indicatively, such as Figure 4 As shown, Figure 4 This is a schematic diagram of the internal structure of a computer device 300 provided in an embodiment of this application. The computer device 300 can be provided as a server. (Refer to...) Figure 4 The computer device 300 includes a processing component 302, which further includes one or more processors, and memory resources represented by memory 301 for storing instructions, such as application programs, that can be executed by the processing component 302. The application programs stored in memory 301 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 302 is configured to execute instructions to perform the product list content richness evaluation method of any of the above embodiments.

[0116] The computer device 300 may also include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate on an operating system stored in memory 301, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or similar.

[0117] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0118] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0119] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0120] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for evaluating the richness of product list content, characterized in that, The method includes: When testing the richness of the product list content of the system under test, at least one test user requests a product list for the same search term. The product list contains multiple product slots, and different product slots at different positions display different product information. When multiple test users request multiple product lists, the product information displayed in the same position of the product slots in different product lists is different. According to a preset statistical dimension, the product features of the product information displayed in product slots at different positions in at least one of the product lists are statistically analyzed to determine the number of features of the product features statistically analyzed under the statistical dimension for the product information displayed in product slots at all positions in at least one of the product lists, and the feature weight of each product feature in product slots at all positions in at least one of the product lists. The richness of the product list content of the system under test is evaluated based on the number of features of the product features displayed in the product slots at all positions in at least one of the product lists under the statistical dimension, and the feature weight of each product feature in the product slots at all positions in at least one of the product lists. This evaluation includes: If the number of features of the product information displayed in the product slots at all positions in at least one of the product lists under the statistical dimension exceeds a preset feature number threshold, and the weight difference of the feature weights of each product feature in the product slots at all positions in at least one of the product lists does not exceed a preset weight difference threshold, then the richness of the product list content of the system under test under the statistical dimension is higher than a preset richness threshold. If the number of features of the product information displayed in all positions of the product list under the statistical dimension does not exceed a preset feature number threshold, and the weight difference of the feature weights of each product feature in all positions of the product list exceeds a preset weight difference threshold, then the richness of the product list content of the system under test under the statistical dimension is lower than a preset richness threshold.

2. The method for evaluating the richness of product list content according to claim 1, characterized in that, The step involves statistically analyzing the product features of product information displayed in at least one product slot at different locations in the product list according to a preset statistical dimension, and determining the number of features of the product features statistically analyzed under the statistical dimension for product information displayed in at least one product slot at all locations in the product list. This includes: When there is only one product list, the product features of the product information displayed in the product slots at different positions in the product list are statistically analyzed according to a preset statistical dimension to obtain a first statistical result. Duplicate product features in the first statistical result are removed, and the number of product features of the product information displayed in the product slots at all positions in the product list under the statistical dimension is determined based on the removed first statistical result. When there are multiple product lists, the product features of the product information displayed in different positions in each product list are statistically analyzed according to a preset statistical dimension to obtain a second statistical result. Duplicate product features in the second statistical result are removed, and the number of product features of the product information displayed in all positions in all product lists under the statistical dimension is determined based on the removed second statistical result.

3. The method for evaluating the richness of product list content according to claim 1, characterized in that, The exposure weight of product slots in different positions within the same product list is different, while the exposure weight of product slots in the same position within different product lists is the same. The step involves statistically analyzing the product features of product information displayed in product slots at different locations in at least one of the product lists according to a preset statistical dimension, and determining the feature weight of each product feature in all product slots at at least one location in the product list, including: According to the preset statistical dimensions, the product features of the product information displayed in the product slots at different positions in at least one of the product lists are statistically analyzed to obtain multiple product features; For each product feature: Count the number of product lists corresponding to the product feature in product slots at different positions in at least one of the product lists, and obtain the number of users corresponding to the product feature in each product slot, wherein each test user corresponds to one product list; Based on the exposure weight of the product slots at each location, the number of users corresponding to the product feature in each product slot, and the total number of test users, calculate the feature weight of the product feature in all product slots at at least one location in the product list.

4. The method for evaluating the richness of product list content according to claim 1, characterized in that, The exposure weight of product slots at different locations in the same product list is set based on the probability that the product information in that slot will be exposed, and the exposure weight of the product slot is positively correlated with the probability that the product information in that slot will be exposed.

5. The method for evaluating the richness of product list content according to claim 1, characterized in that, When testing the richness of the product list content of the system under test, before at least one test user requests the product list for the same search term, the process further includes: Configure the settings for testing the richness of the product list content in the system under test; The configuration information includes the search terms set for the product list to be tested, the simulated test users when requesting the product list to be tested, the number of test users, and the statistical dimensions used to evaluate the richness of the content of the product list to be tested.

6. The method for evaluating the richness of product list content according to any one of claims 1-5, characterized in that, The method further includes: The evaluation results are stored in a database, and an evaluation report corresponding to the evaluation results is generated in the database.

7. A device for evaluating the richness of product list content, characterized in that, include: The data acquisition module is used to acquire the product list requested by at least one test user for the same search term when testing the richness of the product list content of the system under test. The product list contains multiple product slots, and the product slots at different positions display different product information. When multiple test users request multiple product lists, the product information displayed in the same position of the product slots in different product lists is different. The data statistics module is used to statistically analyze the product features of the product information displayed in product slots at different positions in at least one of the product lists according to a preset statistical dimension, and to determine the number of features of the product features of the product information displayed in product slots at all positions in at least one of the product lists under the statistical dimension, as well as the feature weight of each product feature in product slots at all positions in at least one of the product lists. The richness assessment module is used to assess the richness of the product list content of the system under test under the statistical dimension based on the number of features of the product features displayed in the product slots at all positions in at least one of the product lists, and the feature weight of each product feature in the product slots at all positions in at least one of the product lists. This includes: If the number of features of the product information displayed in the product slots at all positions in at least one of the product lists under the statistical dimension exceeds a preset feature number threshold, and the weight difference of the feature weights of each product feature in the product slots at all positions in at least one of the product lists does not exceed a preset weight difference threshold, then the richness of the product list content of the system under test under the statistical dimension is higher than a preset richness threshold. If the number of features of the product information displayed in all positions of the product list under the statistical dimension does not exceed a preset feature number threshold, and the weight difference of the feature weights of each product feature in all positions of the product list exceeds a preset weight difference threshold, then the richness of the product list content of the system under test under the statistical dimension is lower than a preset richness threshold.

8. A storage medium, characterized in that: The storage medium stores computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the product list content richness assessment method as described in any one of claims 1 to 6.

9. A computer device, characterized in that, include: One or more processors, and memory; The memory stores computer-readable instructions, which, when executed by the one or more processors, perform the steps of the product list content richness assessment method as described in any one of claims 1 to 6.

Images