Information generation method, apparatus, device, computer-readable medium, and program product

Abstract

Embodiments of the present disclosure disclose information generation methods, devices, equipment, computer readable media and program products. A specific embodiment of the method comprises: obtaining user report information of a target user; obtaining a pre-constructed historical user report information cluster set; determining a historical user report information cluster to which the user report information belongs as a target historical user report information cluster; filtering historical user report information that meets a preset association condition with the user report information in the target historical user report information cluster as candidate historical user report information, obtaining at least one candidate historical user report information; and determining an item value transfer ladder value proportion for the target user according to a proportion of each item value transfer ladder value included in the at least one candidate historical user report information. The embodiment is related to artificial intelligence and can generate a more accurate item value transfer ladder value proportion.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of computer technology, and more specifically to information generation methods, apparatus, devices, computer-readable media, and program products. Background Technology

[0002] For centralized circulation operations of bulk goods, users often protect their interests by setting tiered value transfer percentages. The determination of these tiered value transfer percentages is typically done manually by the users based on their experience.

[0003] However, the inventors discovered that when using the above method to determine the percentage of value transfer ladder values ​​for goods, the following technical problems often arise:

[0004] The numerical proportions of the value transfer ladder for goods are often inaccurate, which significantly affects the efficiency of goods supply to users and the stability of supply.

[0005] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0007] Some embodiments of this disclosure provide information generation methods, apparatuses, devices, computer-readable media, and program products to address the technical problems mentioned in the background section above.

[0008] In a first aspect, some embodiments of this disclosure provide an information generation method, including: acquiring user-submitted information of a target user, wherein the target user is a user whose item value transfer ladder percentage is to be determined; acquiring a pre-constructed set of historical user-submitted information clusters, wherein each historical user-submitted information cluster in the historical user-submitted information cluster includes: item value transfer ladder percentage; determining the historical user-submitted information cluster to which the user-submitted information belongs in the set of historical user-submitted information clusters as a target historical user-submitted information cluster; filtering historical user-submitted information from the target historical user-submitted information cluster whose information association relationship with the user-submitted information meets a preset association condition as candidate historical user-submitted information, obtaining at least one candidate historical user-submitted information; and determining the item value transfer ladder percentage for the target user based on the item value transfer ladder percentages included in the at least one candidate historical user-submitted information.

[0009] Optionally, the aforementioned user-reported information includes: discrete reporting information and continuous reporting information. The discrete reporting information includes: a discrete reporting feature information set, and the continuous reporting information includes: a continuous reporting feature information set. Determining the historical user-reported information cluster to which the aforementioned user-reported information belongs within the aforementioned historical user-reported information cluster set includes: encoding each discrete reporting feature information in the aforementioned discrete reporting feature information set to obtain an encoded information set for the aforementioned discrete reporting information; normalizing each continuous reporting feature information in the aforementioned continuous reporting feature information set to obtain a normalized information set for the aforementioned continuous reporting information; determining the cluster center of each historical user-reported information cluster in the aforementioned historical user-reported information cluster set to obtain a cluster center set; and determining the historical user-reported information cluster to which the aforementioned user-reported information belongs based on the aforementioned cluster center set, the aforementioned encoded information set, and the aforementioned normalized information set.

[0010] Optionally, determining the historical user-reported information cluster to which the user-reported information belongs based on the cluster center set, the encoded information set, and the normalized information set includes: for each cluster center in the cluster center set, determining the target encoded information set and the target normalized information set corresponding to the cluster center; for each encoded piece of information in the encoded information set, determining the difference value between the encoded piece of information and the target encoded piece of information corresponding to the target encoded information set; for each normalized piece of information in the normalized information set, determining the distance value between the normalized piece of information and the target normalized piece of information corresponding to the target normalized information set; and determining the historical user-reported information cluster to which the user-reported information belongs based on the obtained difference value set and the obtained distance value set.

[0011] Optionally, determining the percentage of item value transfer tiers for the target user based on the percentage of each item value transfer tier included in the information submitted by at least one candidate historical user includes: performing a weighted summation on the percentages of each item value transfer tier to generate a weighted summation value, which is then used as the percentage of item value transfer tiers for the target user.

[0012] Optionally, the aforementioned historical user report information clusters are generated through the following steps: obtaining a set of historical user report information for a set of historical users; determining the number of cluster centers; preprocessing the aforementioned historical user report information set to obtain a preprocessed set of historical user report information; dividing the aforementioned preprocessed set of historical user report information into clusters according to the number of cluster centers to obtain a preprocessed set of historical user report information clusters; and generating a set of historical user report information clusters corresponding to the aforementioned preprocessed set of historical user report information clusters.

[0013] Optionally, the above-mentioned clustering of the preprocessed historical user-reported information set according to the number of cluster centers to obtain a preprocessed historical user-reported information cluster set includes: for every two preprocessed historical user-reported information pieces in the above-mentioned preprocessed historical user-reported information set, inputting the two preprocessed historical user-reported information pieces into a text similarity generation model to generate a similarity value for the two preprocessed historical user-reported information pieces; for each preprocessed historical user-reported information piece in the above-mentioned preprocessed historical user-reported information set, performing a distance value determination step: determining multiple similarity values ​​associated with the above-mentioned preprocessed historical user-reported information piece; determining the weighted average value corresponding to the multiple similarity values; and determining the weighted average value as the distance value for the above-mentioned preprocessed historical user-reported information piece. The distance values ​​of the reported information are obtained; the obtained set of reported information distance values ​​is sorted to obtain a sequence of reported information distance values; reported information distance values ​​whose differences between adjacent reported information distance values ​​satisfy a preset condition are selected from the above reported information distance value sequence as target reported information distance values, resulting in multiple target reported information distance values, wherein the number of target reported information distance values ​​included in the above multiple target reported information distance values ​​is equal to the number of cluster centers; multiple preprocessed historical user reported information corresponding to the above multiple target reported information distance values ​​are determined as the cluster centers of each preprocessed historical user reported information cluster; based on the cluster centers of each preprocessed historical user reported information cluster, the above preprocessed historical user reported information set is clustered to obtain the above preprocessed historical user reported information cluster set.

[0014] Optionally, the above method further includes: sending the percentage of the item value transfer tier for the target user to the user display terminal corresponding to the target user.

[0015] Secondly, some embodiments of this disclosure provide an information generation apparatus, including: a first acquisition unit configured to acquire user-submitted information of a target user, wherein the target user is a user whose item value transfer step value percentage is to be determined; a second acquisition unit configured to acquire a pre-constructed set of historical user-submitted information clusters, wherein each historical user-submitted information cluster in the historical user-submitted information cluster includes: item value transfer step value percentage; a first determination unit configured to determine the historical user-submitted information cluster to which the user-submitted information belongs in the set of historical user-submitted information clusters, as a target historical user-submitted information cluster; a filtering unit configured to filter historical user-submitted information from the target historical user-submitted information clusters that has an information association relationship with the user-submitted information that meets a preset association condition, as candidate historical user-submitted information, to obtain at least one candidate historical user-submitted information; and a second determination unit configured to determine the item value transfer step value percentage for the target user based on the item value transfer step value percentages included in the at least one candidate historical user-submitted information.

[0016] Optionally, the aforementioned user-reported information includes: discrete reporting information and continuous reporting information. The discrete reporting information includes: a discrete reporting feature information set, and the continuous reporting information includes: a continuous reporting feature information set. The first determining unit can be configured to: encode each discrete reporting feature information in the discrete reporting feature information set to obtain an encoded information set for the discrete reporting information; normalize each continuous reporting feature information in the continuous reporting feature information set to obtain a normalized information set for the continuous reporting information; determine the cluster center of each historical user-reported information cluster in the historical user-reported information cluster set to obtain a cluster center set; and determine the historical user-reported information cluster to which the user-reported information belongs based on the cluster center set, the encoded information set, and the normalized information set.

[0017] Optionally, the first determining unit can be configured to: for each cluster center in the aforementioned cluster center set, determine the target encoded information set and the target normalized information set corresponding to the aforementioned cluster center; for each encoded information in the aforementioned encoded information set, determine the difference value between the aforementioned encoded information and the target encoded information corresponding to the aforementioned target encoded information set; for each normalized information in the aforementioned normalized information set, determine the distance value between the aforementioned normalized information and the target normalized information corresponding to the aforementioned target normalized information set; and determine the historical user-reported information cluster to which the aforementioned user-reported information belongs based on the obtained difference value set and the obtained distance value set.

[0018] Optionally, the second determining unit can be configured to: perform a weighted summation on the value transfer ladder percentages of each of the above items to generate a weighted summation value, which serves as the value transfer ladder percentage for the target user.

[0019] Optionally, the aforementioned historical user report information clusters are generated through the following steps: obtaining a set of historical user report information for a set of historical users; determining the number of cluster centers; preprocessing the aforementioned historical user report information set to obtain a preprocessed set of historical user report information; dividing the aforementioned preprocessed set of historical user report information into clusters according to the number of cluster centers to obtain a preprocessed set of historical user report information clusters; and generating a set of historical user report information clusters corresponding to the aforementioned preprocessed set of historical user report information clusters.

[0020] Optionally, the cluster partitioning unit can be configured to: for every two preprocessed historical user reports in the aforementioned preprocessed historical user report set, input the two preprocessed historical user reports into a text similarity generation model to generate a similarity value for the two preprocessed historical user reports; for each preprocessed historical user report in the aforementioned preprocessed historical user report set, perform a distance value determination step: determine multiple similarity values ​​associated with the aforementioned preprocessed historical user reports; determine the weighted average value corresponding to the multiple similarity values; determine the weighted average value as the reporting information distance value for the aforementioned preprocessed historical user reports; and determine the distance value of the obtained reporting information distance value. The set is sorted to obtain a sequence of distance values ​​for reported information; from the above sequence of distance values ​​for reported information, the distance values ​​of reported information that satisfy a preset condition are selected as target distance values ​​for reported information, resulting in multiple target distance values ​​for reported information, wherein the number of target distance values ​​included in the above multiple target distance values ​​is equal to the number of cluster centers; the multiple preprocessed historical user reported information corresponding to the above multiple target distance values ​​are determined as the cluster centers of each preprocessed historical user reported information cluster; based on the cluster centers of each preprocessed historical user reported information cluster, the above set of preprocessed historical user reported information is clustered to obtain the above set of preprocessed historical user reported information clusters.

[0021] Optionally, the above-mentioned device further includes: sending the percentage of the item value transfer ladder for the target user to the user display terminal corresponding to the target user.

[0022] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, such that when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any implementation of the first aspect.

[0023] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method as described in any implementation of the first aspect.

[0024] Fifthly, some embodiments of this disclosure provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0025] The above embodiments of this disclosure have the following beneficial effects: the information generation method of some embodiments of this disclosure can generate more accurate item value transfer ladder numerical proportions. Specifically, the reason why the relevant item value transfer ladder numerical proportions are not accurate enough is that the set item value transfer ladder numerical proportions often have inaccuracies, which greatly affects the item supply efficiency of the supplying user and the stability of supply. Based on this, the information generation method of some embodiments of this disclosure firstly obtains user reporting information of the target user. The target user can be a user whose item value transfer ladder numerical proportion is to be determined. Here, the obtained user reporting information is used to determine the historical user reporting information cluster to which it belongs and at least one candidate historical user reporting information whose association with the user reporting information meets the preset association conditions. Next, a pre-constructed historical user reporting information cluster set is obtained. Each historical user reporting information in the historical user reporting information cluster includes: item value transfer ladder numerical proportion. Here, by obtaining the historical user reporting information cluster set, it is subsequently used to determine the historical user reporting information cluster to which it belongs and at least one candidate historical user reporting information whose association with the user reporting information meets the preset association conditions. Then, the historical user report information clusters to which the aforementioned user report information belongs are identified as target historical user report information clusters. Here, each historical user report information in the identified target historical user report information cluster shares a certain degree of feature similarity with the user report information. Therefore, identifying the target historical user report information cluster also facilitates the subsequent identification of at least one candidate historical user report information with more similar features. Furthermore, at least one candidate historical user report information whose information relationship with the aforementioned user report information satisfies a preset association condition is selected from the target historical user report information cluster for subsequent determination of the item value transfer tier percentage. Finally, based on the item value transfer tier percentages included in the at least one candidate historical user report information, the item value transfer tier percentage for the target user can be accurately determined, improving the supply efficiency and stability of the supply to the user. Attached Figure Description

[0026] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0027] Figure 1 This is a schematic diagram illustrating an application scenario of an information generation method according to some embodiments of the present disclosure;

[0028] Figure 2This is a flowchart of some embodiments of the information generation method according to this disclosure;

[0029] Figure 3 This is a flowchart of some other embodiments of the information generation method according to this disclosure;

[0030] Figure 4 This is a schematic diagram illustrating the generation of historical user-submitted information clusters according to some embodiments of the information generation method of this disclosure;

[0031] Figure 5 These are schematic diagrams illustrating the structure of some embodiments of the information generation apparatus according to this disclosure;

[0032] Figure 6 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0033] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0034] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0035] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0036] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0037] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0038] Before performing any of the operations involving the collection, storage, or use of user personal information (such as information submitted by users) as disclosed in this disclosure, the relevant organizations or individuals shall fulfill their obligations, including conducting personal information security impact assessments, informing personal information subjects, and obtaining prior authorization and consent from personal information subjects.

[0039] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0040] Figure 1 This is a schematic diagram illustrating an application scenario of an information generation method according to some embodiments of the present disclosure.

[0041] exist Figure 1In this application scenario, firstly, electronic device 101 can obtain user reporting information 103 from target user 102. Target user 102 can be a user whose percentage of the item value transfer ladder value is to be determined. In this application scenario, user reporting information 103 can be: "Monthly committed order volume: 1000 orders, average order weight: 5kg, region: Beijing". Then, electronic device 101 can obtain a pre-built historical user reporting information cluster set 104. Each historical user reporting information in the historical user reporting information cluster includes: percentage of the item value transfer ladder value. Next, electronic device 101 can determine the historical user reporting information cluster to which user reporting information 103 belongs within the historical user reporting information cluster set 104, and use it as the target historical user reporting information cluster. In this application scenario, historical user reporting information cluster set 104 includes: historical user reporting information cluster 105, historical user reporting information cluster 106, and historical user reporting information cluster 107. Historical user report information cluster 105 may include: historical user report information 1051, historical user report information 1052, historical user report information 1053, and historical user report information 1054. Historical user report information cluster 106 may include: historical user report information 1061 and historical user report information 1062. Historical user report information cluster 107 may include: historical user report information 1071, historical user report information 1072, and historical user report information 1073. The aforementioned target historical user report information cluster may be historical user report information cluster 105. Furthermore, the electronic device 101 can filter historical user report information from the aforementioned target historical user report information cluster that satisfies the preset association conditions with the aforementioned user report information 103, as candidate historical user report information, to obtain at least one candidate historical user report information 108. In this application scenario, at least one candidate historical user submission information 108 may include: candidate historical user submission information 1081 corresponding to historical user submission information 1051, candidate historical user submission information 1082 corresponding to historical user submission information 1052, and candidate historical user submission information 1083 corresponding to historical user submission information 1053. Finally, the electronic device 101 can determine the item value transfer step value percentage 110 for the target user 102 based on the item value transfer step value percentage 109 included in the at least one candidate historical user submission information 108. In this application scenario, the item value transfer step value percentage 109 includes: the item value transfer step value percentage 1091 included in candidate historical user submission information 1081, the item value transfer step value percentage 1092 included in candidate historical user submission information 1082, and the item value transfer step value percentage 1093 included in candidate historical user submission information 1083.

[0042] It should be noted that the aforementioned electronic device 101 can be either hardware or software. When the electronic device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the electronic device is software, it can be installed in the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0043] It should be understood that Figure 1 The number of electronic devices shown is merely illustrative. Any number of electronic devices can be used depending on the implementation requirements.

[0044] Continue to refer to Figure 2 The flowchart 200 illustrates some embodiments of the information generation method according to this disclosure. The information generation method includes the following steps:

[0045] Step 201: Obtain the user submission information of the target user.

[0046] In some embodiments, the execution subject of the above information generation method (e.g. Figure 1 The electronic device 101 shown can acquire user-submitted information from target users via wired or wireless connection. The target user can be a user whose percentage of the value transfer tier is to be determined. In practice, the percentage of the value transfer tier can be a tiered discount offer. The user-submitted information can be the offer information submitted by the target user for the target item. In practice, the user-submitted information can be in the form of a price list. The price information includes: characteristic information of each price feature. The characteristic information is the characteristic value of the price feature. For example, the price feature is the monthly committed order volume, corresponding to a characteristic value of 100 orders. Specifically, each price feature can include, but is not limited to, one of the following: the user's monthly committed order volume, the user's income during the target period, average weight per order, average volume per order, the user's location, the third-level category corresponding to the target item, the user's contracted discount, and the user's actual discount. The user's monthly committed order volume can be the number of orders the user commits to supply for the target item. The user's income during the target period can be the user's annual income. The average weight per order can be the weight of each target item in order. The average volume per order can be the volume of each target item in order. A user's contractual discount can be a price discount agreed upon between the user and the purchasing user for the target item. A user's actual discount can be the actual price discount for the target item negotiated between the user and the purchasing user.

[0047] For example, if the target item is "apple", the corresponding tiered discount price could be: {[0-500 orders, 90% off], [501-1000 orders, 80% off], [1001-3000 orders, 70% off], [3001-5000 orders, 60% off], [5001+ orders, 50% off]}.

[0048] Step 202: Obtain a pre-built cluster of historical user-submitted information.

[0049] In some embodiments, the aforementioned executing entity can acquire a pre-built cluster of historical user submissions via wired or wireless means. Each historical user submission within a cluster includes a percentage of the item's value transfer threshold. The characteristic information among the historical user submissions in each cluster is relatively similar. Each historical user submission in the cluster corresponds one-to-one with a historical user. A historical user can be a user whose percentage of the item's value transfer threshold has been determined. Each historical user submission in the cluster includes a pre-determined percentage of the item's value transfer threshold. The historical user submissions in the cluster represent the price quotes submitted by historical users for the target item.

[0050] It should be noted that the number of historical user-reported information clusters included in the above-mentioned historical user-reported information clusters can be preset.

[0051] In some optional implementations of certain embodiments, the aforementioned historical user-reported information cluster is generated through the following steps:

[0052] The first step is to obtain the set of historical user reports for the historical user set.

[0053] The historical users in the historical user set are those whose percentage of the item value transfer ladder has been determined. There is a one-to-one correspondence between the historical users in the aforementioned historical user set and the historical user submissions in the aforementioned historical user submission information set. The historical user submission information includes feature information for each pricing characteristic. For example, each pricing characteristic may include, but is not limited to, one of the following: the user's monthly committed order volume, the user's income during the target time period, average order weight, average order volume, the user's location, the third-level category corresponding to the target item, the user's contracted discount, the user's actual discount, and the percentage of the item value transfer ladder corresponding to the historical user.

[0054] The second step is to determine the number of cluster centers.

[0055] As an example, firstly, the aforementioned executing entity can determine the number of historical users included in the historical user set. Then, based on the number of users and a preset ratio, the number of cluster centers is determined. The preset ratio can be the ratio between the number of users and the number of cluster centers. For example, the preset ratio could be "100:1". If the number of users is 10,000, then the number of cluster centers could be 100.

[0056] Alternatively, the number of cluster centers mentioned above can be determined using the Gap Statistic method.

[0057] The third step is to preprocess the above-mentioned historical user-submitted information set to obtain the preprocessed historical user-submitted information set.

[0058] As an example, the aforementioned executing entity can populate each historical user report in the aforementioned historical user report information set with information to generate populated historical user report information, which serves as preprocessed historical user report information, thus obtaining a preprocessed historical user report information set.

[0059] Optionally, the preprocessed historical user reporting information in the preprocessed historical user reporting information set can be information in vector form.

[0060] The fourth step is to divide the preprocessed historical user-submitted information set into clusters based on the number of cluster centers mentioned above, thereby obtaining the preprocessed historical user-submitted information cluster set.

[0061] As an example, firstly, the aforementioned execution entity can randomly extract a target number of preprocessed historical user reports from the preprocessed historical user report set. This target number can be equal to the number of cluster centers. Then, the execution entity can remove the target number of preprocessed historical user reports from the preprocessed historical user report set, obtaining a set of removed historical user reports. Next, the execution entity can determine the vector distance between each historical user report in the removed historical user report set and the target number of preprocessed historical user reports, obtaining a set of vector distances. Then, for each historical user report in the removed historical user report set, the shortest vector distance in the vector distance set corresponding to that historical user report is determined, and the preprocessed historical user report corresponding to the shortest vector distance from the target number of preprocessed historical user reports is determined as the target historical user report. Finally, for each historical user report in the removed historical user report set, the aforementioned historical user report is added to the preprocessed historical user report cluster centered on the target historical user report.

[0062] The fifth step is to generate a historical user report information cluster corresponding to the historical user report information cluster set after preprocessing as described above.

[0063] As an example, the aforementioned executing entity can generate a historical user report information cluster corresponding to the aforementioned preprocessed historical user report information cluster by using a relationship table that represents the correspondence between the preprocessed historical user report information and the historical user report information.

[0064] like Figure 3 The diagram illustrates the generation of historical user-reported information clusters. First, a historical user-reported information set 301 is obtained for the historical user set. Each square in the historical user-reported information set 301 represents historical user-reported information. Then, the number of cluster centers is determined to be 3. Next, the historical user-reported information set 301 is preprocessed to obtain a preprocessed historical user-reported information set 302. Each circle in the preprocessed historical user-reported information set 302 represents preprocessed historical user-reported information. Furthermore, based on the number of cluster centers, the preprocessed historical user-reported information set 302 is clustered to obtain a preprocessed historical user-reported information cluster set 303. The preprocessed historical user-reported information cluster set 303 includes: preprocessed historical user-reported information cluster 3031, preprocessed historical user-reported information cluster 3032, and preprocessed historical user-reported information cluster 3033. In this process, the black-filled circles in preprocessed historical user report information cluster 3031 serve as cluster centers. The black-filled circles in preprocessed historical user report information cluster 3032 and 3033 also serve as cluster centers. Finally, a historical user report information cluster set 304 corresponding to the preprocessed historical user report information cluster set 303 is generated. This historical user report information cluster set 304 includes historical user report information clusters 3041, 3042, and 3043. In historical user report information cluster 3041, the black-filled squares serve as cluster centers. In historical user report information cluster 3042, the black-filled squares serve as cluster centers. In historical user report information cluster 3043, the black-filled squares serve as cluster centers.

[0065] Optionally, based on the number of cluster centers, the preprocessed historical user-reported information set is divided into clusters to obtain a preprocessed historical user-reported information cluster set, including:

[0066] The first step is to input every two preprocessed historical user reports in the above preprocessed historical user report set into the text similarity generation model to generate a similarity value for the two preprocessed historical user reports.

[0067] The text similarity generation model described above can be a neural network model that determines the content similarity between two texts. For example, the text similarity generation model described above can be a DSSM (Deep Structured Semantic Model) model. The similarity value can be a value between [0, 1].

[0068] The second step is to perform a distance value determination step for each preprocessed historical user report in the aforementioned preprocessed historical user report set:

[0069] The first sub-step involves determining multiple similarity values ​​associated with the preprocessed historical user-submitted information.

[0070] The number of similarities corresponding to multiple similarity values ​​is equal to the number of preprocessed historical user-submitted information corresponding to the preprocessed historical user-submitted information set minus the value "1".

[0071] As an example, multiple similarity values ​​associated with the preprocessed historical user-submitted information can be determined by querying similarity values.

[0072] The second sub-step is to determine the weighted average value corresponding to the above multiple similarity values.

[0073] The weighted average of each similarity value can be pre-set. For example, given multiple similarity values ​​{0.3, 0.4, 0.3}, the weighted average could be: 0.34. The weighted average for a similarity value of 0.3 would be: 0.34.

[0074] The third sub-step is to determine the weighted average value as the distance value of the reported information to the preprocessed historical user reported information.

[0075] The third step is to sort the obtained distance value set of the reported information to obtain the distance value sequence of the reported information.

[0076] As an example, the distance value set of the reported information is sorted in ascending order to obtain the distance value sequence of the reported information.

[0077] For example, the distance value set for the reported information is: {0.2, 0.21, 0.32, 0.42, 0.48, 0.53, 0.62, 0.71, 0.83}.

[0078] The fourth step is to filter out the distance values ​​of adjacent reported information that meet the preset conditions from the above sequence of distance values ​​of reported information, and use them as the target distance values ​​of reported information, thus obtaining multiple target distance values ​​of reported information.

[0079] The number of target reporting information distance values ​​included in the aforementioned multiple target reporting information distance values ​​is equal to the number of cluster centers. The difference between adjacent reporting information distance values ​​can be obtained by subtracting the previous distance difference from the subsequent distance difference corresponding to the reporting information distance value. The previous distance difference of the first reporting information distance value in the aforementioned set of reporting information distance values ​​can be the difference between the first reporting information distance value and the value "0". The previous distance difference of the last reporting information distance value in the aforementioned set of reporting information distance values ​​can be the difference between the value "1" and the last reporting information distance value. A preset condition can be that the size of the adjacent reporting information distance differences ranks among the top number of cluster centers.

[0080] For example, the distance value set for the reported information is: {0.1, 0.21, 0.32, 0.48, 0.53, 0.62, 0.71, 0.92}. The distance difference between the preceding and following distance values ​​corresponding to a reported information distance value of "0.1" can be "0.1". The distance difference between the following distance values ​​corresponding to a reported information distance value of "0.1" can be "0.11". Therefore, the distance difference between adjacent reported information corresponding to a value of "0.1" is "0.01". Similarly, the distance difference between the preceding and following distance values ​​corresponding to a reported information distance value of "0.21" can be "0.01". The distance difference between the following distance values ​​corresponding to a reported information distance value of "0.21" can be "0.11". Therefore, the distance difference between adjacent reported information corresponding to a value of "0.21" is "0.01". The distance difference between the preceding and following distance values ​​corresponding to a reported information distance value of "0.32" can be "0.11". The distance difference for a reported message with a value of "0.32" can be followed by a distance difference of "0.16". Therefore, the distance difference between adjacent reported messages with a value of "0.32" is "0.05". The distance difference for a reported message with a value of "0.48" can be followed by a distance difference of "0.16". The distance difference for a reported message with a value of "0.48" can be followed by a distance difference of "0.06". Therefore, the distance difference between adjacent reported messages with a value of "0.48" is "-0.1". The distance difference for a reported message with a value of "0.53" can be followed by a distance difference of "0.09". The distance difference for a reported message with a value of "0.53" can be followed by a distance difference of "0.09". Therefore, the distance difference between adjacent reported messages with a value of "0.53" is "0.03". The distance difference for a reported message with a value of "0.62" can be followed by a distance difference of "0.09". The distance difference between the next reported information value of "0.62" and the reported information value of "0.62" can be "0.09". Therefore, the distance difference between adjacent reported information values ​​of "0.62" is "0". The distance difference between the previous reported information value of "0.71" and the reported information value of "0.71" can be "0.21". Therefore, the distance difference between adjacent reported information values ​​of "0.71" is "0.12". The distance difference between the previous reported information value of "0.92" and the reported information value of "0.92" can be "0.21". The distance difference between the next reported information value of "0.92" and the reported information value of "0.08" can be "0.08". Therefore, the distance difference between adjacent reported information values ​​of "0.92" is "-0.13". The number of cluster centers can be "2".

[0081] The target reporting distance values ​​include: a target reporting distance of "0.32" and a target reporting distance of "0.71".

[0082] The fifth step is to determine the cluster centers of the multiple preprocessed historical user reports corresponding to the distance values ​​of the multiple target reports as the cluster centers of each preprocessed historical user report cluster.

[0083] The sixth step is to divide the preprocessed historical user-submitted information set into clusters based on the cluster centers of each preprocessed historical user-submitted information cluster, thereby obtaining the preprocessed historical user-submitted information cluster set.

[0084] As an example, based on the cluster centers of the aforementioned preprocessed historical user-reported information clusters, the aforementioned preprocessed historical user-reported information set is divided into clusters to obtain the aforementioned preprocessed historical user-reported information cluster set. This may include the following steps:

[0085] Sub-step 1: Remove each cluster center from the preprocessed historical user report information set to obtain the removed historical user report information set.

[0086] Sub-step 2: For each historical user report in the removed historical user report set, determine the vector distance between the historical user report and each cluster center to obtain the vector distance set.

[0087] Sub-step 3: For each historical user report in the removed historical user report set, determine the minimum vector distance in the corresponding vector distance set, and determine the cluster center corresponding to the minimum vector distance, as the target cluster center.

[0088] Sub-step 4: For each historical user report in the removed historical user report set, add the aforementioned historical user report to the set corresponding to the target cluster center.

[0089] Step 203: Determine the historical user reporting information cluster to which the aforementioned user reporting information belongs within the aforementioned historical user reporting information cluster set, and use it as the target historical user reporting information cluster.

[0090] In some embodiments, the aforementioned executing entity may determine the historical user reporting information cluster to which the aforementioned user reporting information belongs within the aforementioned historical user reporting information cluster set as the target historical user reporting information cluster.

[0091] As an example, firstly, the aforementioned execution entity can encode the cluster centers corresponding to the historical user-submitted information clusters to generate vector encoding vectors, thus obtaining a set of encoded vectors. Then, the aforementioned execution entity can perform vector encoding on the user-submitted information to generate user-submitted information encoded vectors. Next, the aforementioned execution entity can determine the distances between the user-submitted information encoded vectors and each encoded vector in the encoded vector set, thus obtaining a distance set. Furthermore, the cluster center corresponding to the smallest distance in the aforementioned distance set is determined as the target cluster center. Finally, the aforementioned execution entity can determine the target historical user-submitted information cluster based on the historical user-submitted information clusters corresponding to the target cluster center.

[0092] In some optional implementations of certain embodiments, the aforementioned user-reported information includes: discrete reporting information and continuous reporting information. The discrete reporting information includes: a discrete reporting feature information set, and the continuous reporting information includes: a continuous reporting feature information set. Discrete reporting information can be feature information of multiple discrete reporting features in the user-reported information. Continuous reporting information can be feature information of multiple continuous reporting features in the user-reported information.

[0093] Optionally, determining the historical user report information cluster to which the user report information belongs within the aforementioned historical user report information cluster set may include the following steps:

[0094] The first step is for the aforementioned executing entity to encode each discrete reporting feature in the aforementioned discrete reporting feature information set to obtain an encoded information set for the aforementioned discrete reporting information.

[0095] As an example, the aforementioned execution entity can perform one-hot encoding on each discrete reporting feature in the aforementioned discrete reporting feature information set to obtain an encoded information set for the aforementioned discrete reporting information.

[0096] The second step is for the aforementioned executing entity to normalize each continuous reporting feature in the aforementioned continuous reporting feature information set to obtain a normalized information set for the aforementioned continuous reporting information.

[0097] Third, the aforementioned executing entity can determine the cluster center of each historical user-submitted information cluster in the aforementioned historical user-submitted information cluster set, thus obtaining the cluster center set.

[0098] As an example, the aforementioned execution entity can determine the cluster center of each historical user-submitted information cluster in the aforementioned historical user-submitted information cluster set through various cluster center query methods, thereby obtaining the cluster center set.

[0099] Fourth, the aforementioned executing entity can determine the historical user-submitted information cluster to which the aforementioned user-submitted information belongs based on the aforementioned cluster center set, the aforementioned encoded information set, and the aforementioned normalized information set.

[0100] Optionally, determining the historical user-submitted information cluster to which the user-submitted information belongs based on the cluster center set, the encoded information set, and the normalized information set may include the following steps:

[0101] The first step is that, for each cluster center in the above cluster center set, the execution entity can determine the target encoded information set and the target normalized information set corresponding to the above cluster center.

[0102] Each cluster center possesses corresponding discrete and continuous historical reporting information. Therefore, the generation of the target encoded information set and the target normalized information set for each cluster center will not be elaborated upon here.

[0103] The second step is that, for each piece of encoded information in the aforementioned encoded information set, the executing entity can determine the difference value between the aforementioned encoded information and the target encoded information corresponding to the aforementioned target encoded information set.

[0104] As an example, the encoded information in the encoded information set is a vector after one-hot encoding. The encoded information in the target encoded information set is also a vector after one-hot encoding. The aforementioned execution entity can determine the cosine value between the encoded information and the corresponding target encoded information as the difference value.

[0105] Third, for each piece of normalized information in the above-mentioned normalized information set, the executing entity can determine the distance value between the above-mentioned normalized information and the target normalized information corresponding to the above-mentioned target normalized information set.

[0106] As an example, for each piece of normalized information in the above-mentioned normalized information set, the executing entity can determine the information difference between the normalized information and the target normalized information corresponding to the above-mentioned target normalized information set, as a distance value.

[0107] Fourth, the aforementioned executing entity can determine the historical user-submitted information cluster to which the aforementioned user-submitted information belongs based on the obtained set of difference values ​​and the obtained set of distance values.

[0108] There is a one-to-one correspondence between the difference values ​​in the above difference value set and the distance values ​​in the above distance value set.

[0109] As an example, firstly, the aforementioned execution entity can add the difference values ​​in the difference value set to the distance values ​​in the distance value set to obtain a summation result set. There is a one-to-one correspondence between the summation results in the summation result set and the cluster centers in each cluster center. Then, the summation result with the smallest value is selected from the summation result set as the target summation result. Finally, the historical user-reported information cluster containing the cluster center corresponding to the target summation result is determined as the historical user-reported information cluster to which the aforementioned user-reported information belongs.

[0110] Step 204: Select historical user reports from the target historical user report information cluster that meet the preset association conditions with the above user report information as candidate historical user report information, and obtain at least one candidate historical user report information.

[0111] In some embodiments, the executing entity may filter historical user reports from the target historical user report information cluster that satisfy a preset association condition with the user report information, and use these as candidate historical user reports to obtain at least one candidate historical user report. The association condition may be the feature correlation between the user report information and the target historical user report information. The preset association condition may be at least one historical user report from the target historical user report information cluster that has the highest feature correlation with the user report information.

[0112] As an example, firstly, the aforementioned execution entity can perform vector encoding on each historical user report in the target historical user report information cluster to generate an encoded vector, thus obtaining an encoded vector set. Then, the aforementioned execution entity can perform vector encoding on the user report information to generate a user report information encoded vector. Next, the aforementioned execution entity can determine the distance between the user report information encoded vector and each encoded vector in the encoded vector set, thus obtaining a distance set. Then, it can filter out at least one distance with the smallest corresponding value from the aforementioned distance set. Finally, the aforementioned execution entity can determine at least one historical user report information corresponding to the aforementioned at least one distance as at least one candidate historical user report information.

[0113] Step 205: Determine the percentage of item value transfer ladder values ​​for the target user based on the percentage of each item value transfer ladder value included in the information submitted by at least one candidate historical user.

[0114] In some embodiments, the executing entity may determine the item value transfer tier percentage for the target user based on the item value transfer tier percentages included in the information submitted by at least one candidate historical user. The item value transfer tier percentage may be a tiered discount offer.

[0115] As an example, the aforementioned executing entity can determine the item value transfer ladder data percentage with the highest percentage among the various item value transfer ladder data percentages as the item value transfer ladder value percentage for the aforementioned target user.

[0116] In some optional implementations of certain embodiments, the executing entity may perform a weighted summation of the value transfer tier percentages of each item to generate a weighted sum value, which serves as the value transfer tier percentage for the target user. The weight of each value transfer tier percentage is pre-set.

[0117] For example, the percentage of value transfer tiers for each item is as follows: {First item value transfer tier percentage: {[0-500 orders, 90% off], [501-1000 orders, 80% off], [1001-3000 orders, 70% off], [3001-5000 orders, 60% off], [5001+, 50% off]}, Second item value transfer tier percentage: {[0-500 orders, 80% off], [501-1000+ orders, 70% off], [3001-5000 orders, 60% off], [5001+ orders, 50% off]}, The value transfer thresholds for the first and third tiers of items are as follows: [0-500 orders, 75% off], [1001-3000 orders, 65% off], [3001-5000 orders, 60% off], [5001+ orders, 50% off]}. The weight corresponding to the value transfer threshold for the first tier is 0.4. The weight corresponding to the value transfer threshold for the second tier is 0.3. The weight corresponding to the value transfer threshold for the third tier is 0.3. The percentage of item value transfer tiers for the aforementioned target users is as follows: {[0-500 orders, 8.25% discount], [501-1000 orders, 7.4% discount], [1001-3000 orders, 6.7% discount], [3001-5000 orders, 6% discount], [5001+ orders, 5% discount]}.

[0118] The above embodiments of this disclosure have the following beneficial effects: the information generation method of some embodiments of this disclosure can generate more accurate item value transfer ladder numerical proportions. Specifically, the reason why the relevant item value transfer ladder numerical proportions are not accurate enough is that the set item value transfer ladder numerical proportions often have inaccuracies, which greatly affects the item supply efficiency of the supplying user and the stability of supply. Based on this, the information generation method of some embodiments of this disclosure firstly obtains user reporting information of the target user. The target user can be a user whose item value transfer ladder numerical proportion is to be determined. Here, the obtained user reporting information is used to determine the historical user reporting information cluster to which it belongs and at least one candidate historical user reporting information whose association with the user reporting information meets the preset association conditions. Next, a pre-constructed historical user reporting information cluster set is obtained. Each historical user reporting information in the historical user reporting information cluster includes: item value transfer ladder numerical proportion. Here, by obtaining the historical user reporting information cluster set, it is subsequently used to determine the historical user reporting information cluster to which it belongs and at least one candidate historical user reporting information whose association with the user reporting information meets the preset association conditions. Then, the historical user report information clusters to which the aforementioned user report information belongs are identified as target historical user report information clusters. Here, each historical user report information in the identified target historical user report information cluster shares a certain degree of feature similarity with the user report information. Therefore, identifying the target historical user report information cluster also facilitates the subsequent identification of at least one candidate historical user report information with more similar features. Furthermore, at least one candidate historical user report information whose information relationship with the aforementioned user report information satisfies a preset association condition is selected from the target historical user report information cluster for subsequent determination of the item value transfer tier percentage. Finally, based on the item value transfer tier percentages included in the at least one candidate historical user report information, the item value transfer tier percentage for the target user can be accurately determined, improving the supply efficiency and stability of the supply to the user.

[0119] Further reference Figure 4 The diagram illustrates a flow 400 of another embodiment of the information generation method according to the present disclosure. This information generation method includes the following steps:

[0120] Step 401: Obtain the user submission information of the target user.

[0121] Step 402: Obtain a pre-built cluster of historical user-submitted information.

[0122] Step 403: Determine the historical user reporting information cluster to which the aforementioned user reporting information belongs within the aforementioned historical user reporting information cluster set, and use it as the target historical user reporting information cluster.

[0123] Step 404: Select historical user submission information from the above target historical user submission information cluster that meets the preset association conditions with the above user submission information as candidate historical user submission information, and obtain at least one candidate historical user submission information.

[0124] Step 405: Determine the percentage of item value transfer ladder values ​​for the target user based on the percentage of each item value transfer ladder value included in the information submitted by at least one candidate historical user.

[0125] In some embodiments, the specific implementation of steps 401-405 and the resulting technical effects can be found in [reference needed]. Figure 2 Steps 201-205 in the corresponding embodiments will not be repeated here.

[0126] Step 406: Send the percentage of the item value transfer tier for the target user to the user display terminal corresponding to the target user.

[0127] In some embodiments, the executing entity (e.g. Figure 1 The electronic device 101 shown can send the percentage of the item value transfer tier to the target user to the user's corresponding display terminal. The user display terminal can be a display terminal used by the user to display the percentage of the item value transfer tier. For example, the user display terminal is a mobile phone terminal.

[0128] from Figure 4 It can be seen from this that, with Figure 2 Compared to the description of some corresponding embodiments, Figure 4 In some corresponding embodiments, the information generation method process 400 discloses the display of the item value transfer ladder value percentage for the target item, which facilitates the supplier to adjust the corresponding item value transfer ladder value percentage in a timely manner, thereby improving the item supply efficiency of the supplier.

[0129] Further reference Figure 5 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of an information generation apparatus, which are similar to... Figure 2 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0130] like Figure 5As shown, an information generation device 500 includes: a first acquisition unit 501, a second acquisition unit 502, a first determination unit 503, a filtering unit 504, and a second determination unit 505. The system comprises the following components: a first acquisition unit 501, configured to acquire user-submitted information from a target user, wherein the target user is the user whose item value transfer threshold percentage is to be determined; a second acquisition unit 502, configured to acquire a pre-constructed set of historical user-submitted information clusters, wherein each historical user-submitted information cluster includes an item value transfer threshold percentage; a first determination unit 503, configured to determine the historical user-submitted information cluster to which the user-submitted information belongs, as the target historical user-submitted information cluster; a filtering unit 504, configured to filter historical user-submitted information from the target historical user-submitted information cluster that has a preset association condition with the user-submitted information, as candidate historical user-submitted information, thereby obtaining at least one candidate historical user-submitted information; and a second determination unit 505, configured to determine the item value transfer threshold percentage for the target user based on the item value transfer threshold percentages included in the at least one candidate historical user-submitted information.

[0131] In some optional implementations of certain embodiments, the aforementioned user-reported information includes: discrete reporting information and continuous reporting information. The discrete reporting information includes: a discrete reporting feature information set, and the continuous reporting information includes: a continuous reporting feature information set. The first determining unit 503 in the aforementioned device 500 may be further configured to: encode each discrete reporting feature information in the aforementioned discrete reporting feature information set to obtain an encoded information set for the aforementioned discrete reporting information; normalize each continuous reporting feature information in the aforementioned continuous reporting feature information set to obtain a normalized information set for the aforementioned continuous reporting information; determine the cluster center of each historical user-reported information cluster in the aforementioned historical user-reported information cluster set to obtain a cluster center set; and determine the historical user-reported information cluster to which the aforementioned user-reported information belongs based on the aforementioned cluster center set, the aforementioned encoded information set, and the aforementioned normalized information set.

[0132] In some optional implementations of certain embodiments, the first determining unit 503 in the above-described apparatus 500 may be further configured to: for each cluster center in the cluster center set, determine the target encoded information set and the target normalized information set corresponding to the cluster center; for each encoded information in the encoded information set, determine the difference value between the encoded information and the target encoded information corresponding to the target encoded information set; for each normalized information in the normalized information set, determine the distance value between the normalized information and the target normalized information corresponding to the target normalized information set; and determine the historical user reporting information cluster to which the user reporting information belongs based on the obtained difference value set and the obtained distance value set.

[0133] In some optional implementations of some embodiments, the second determining unit 505 in the above-mentioned device 500 may be further configured to: perform weighted summation on the value transfer ladder values ​​of each of the above-mentioned items to generate a weighted summation value as the value transfer ladder value ratio of the items for the above-mentioned target user.

[0134] In some optional implementations of certain embodiments, the aforementioned historical user report information clusters are generated through the following steps: obtaining a historical user report information set for a historical user set; determining the number of cluster centers; preprocessing the aforementioned historical user report information set to obtain a preprocessed historical user report information set; dividing the aforementioned preprocessed historical user report information set into clusters according to the number of cluster centers to obtain a preprocessed historical user report information cluster set; and generating a historical user report information cluster set corresponding to the aforementioned preprocessed historical user report information cluster set.

[0135] In some optional implementations of certain embodiments, the cluster partitioning unit in the above-described apparatus 500 may be further configured to: for every two preprocessed historical user reports in the above-described preprocessed historical user report information set, input the two preprocessed historical user report information sets into a text similarity generation model to generate a similarity value for the two preprocessed historical user report information sets; for each preprocessed historical user report information set in the above-described preprocessed historical user report information set, perform a distance value determination step: determine multiple similarity values ​​associated with the above-described preprocessed historical user report information; determine the weighted average value corresponding to the multiple similarity values; and determine the weighted average value as the report information distance value for the above-described preprocessed historical user report information. The obtained distance value set of the reported information is sorted to obtain a distance value sequence of reported information; the distance values ​​of reported information whose differences between adjacent reported information distance values ​​satisfy a preset condition are selected from the above distance value sequence as target reported information distance values, resulting in multiple target reported information distance values, wherein the number of target reported information distance values ​​included in the above multiple target reported information distance values ​​is equal to the number of cluster centers; the multiple preprocessed historical user reported information corresponding to the above multiple target reported information distance values ​​are determined as the cluster centers of each preprocessed historical user reported information cluster; based on the cluster centers of each preprocessed historical user reported information cluster, the above preprocessed historical user reported information set is clustered to obtain the above preprocessed historical user reported information cluster set.

[0136] In some optional implementations of certain embodiments, the apparatus 500 further includes a sending unit (not shown in the figure). The sending unit can be configured to send the percentage of the item value transfer tier for the target user to the user display terminal corresponding to the target user.

[0137] It is understandable that the units described in the device 500 are related to the reference. Figure 2 The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 500 and the units contained therein, and will not be repeated here.

[0138] The following is for reference. Figure 6 It illustrates electronic devices suitable for implementing some embodiments of this disclosure (e.g., Figure 1 A schematic diagram of the structure of electronic device 101)600 in the middle. Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0139] like Figure 6As shown, electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from storage device 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of electronic device 600. Processing device 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0140] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic device 600 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 An electronic device 600 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 6 Each box shown can represent a device or multiple devices as needed.

[0141] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, it performs the functions defined above in the methods of some embodiments of this disclosure.

[0142] It should be noted that, in some embodiments of this disclosure, the computer-readable medium described above may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0143] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0144] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire user-submitted information from a target user, wherein the target user may be a user whose item value transfer threshold percentage is to be determined; acquire a pre-constructed set of historical user-submitted information clusters, wherein each historical user-submitted information cluster includes: item value transfer threshold percentage; determine the historical user-submitted information cluster to which the aforementioned user-submitted information belongs, as a target historical user-submitted information cluster; filter historical user-submitted information from the target historical user-submitted information cluster whose information association with the aforementioned user-submitted information satisfies a preset association condition, as candidate historical user-submitted information, obtaining at least one candidate historical user-submitted information; and determine the item value transfer threshold percentage for the aforementioned target user based on the item value transfer threshold percentages included in the at least one candidate historical user-submitted information.

[0145] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0146] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0147] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor can be described as including: a first acquisition unit, a second acquisition unit, a first determination unit, a filtering unit, and a second determination unit. The names of these units do not necessarily limit the specific unit; for example, the first acquisition unit can also be described as "a unit for acquiring user-submitted information from a target user."

[0148] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0149] Some embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements any of the above-described information generation methods.

[0150] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. An information generation method, comprising: Obtain user-submitted information from target users, wherein the target users are users whose percentage of the value transfer ladder of the goods to be determined is to be determined. Obtain a pre-built cluster of historical user-reported information, wherein each historical user-reported information in the cluster includes: the percentage of value transfer ladder values ​​for items; Determine the historical user report information cluster to which the user report information belongs within the historical user report information cluster set, and use it as the target historical user report information cluster; Historical user submissions that satisfy preset association conditions and have an information relationship with the user submissions are selected from the target historical user submission information cluster and used as candidate historical user submissions to obtain at least one candidate historical user submission. Based on the percentage of each item value transfer tier included in the information submitted by at least one candidate historical user, the percentage of item value transfer tier for the target user is determined.

2. The method according to claim 1, wherein, The user-submitted information includes: discrete submission information and continuous submission information. The discrete submission information includes: a discrete submission feature information set, and the continuous submission information includes: a continuous submission feature information set; and The step of determining the historical user report information cluster to which the user report information belongs within the historical user report information cluster set includes: Encode each discrete reporting feature in the discrete reporting feature information set to obtain an encoded information set for the discrete reporting information; Normalize each continuous reporting feature in the continuous reporting feature information set to obtain a normalized information set for the continuous reporting information; Determine the cluster center of each historical user-reported information cluster in the historical user-reported information cluster set to obtain the cluster center set; Based on the cluster center set, the encoded information set, and the normalized information set, the historical user submission information cluster to which the user submission information belongs is determined.

3. The method according to claim 2, wherein, The step of determining the historical user report information cluster to which the user report information belongs based on the cluster center set, the encoded information set, and the normalized information set includes: For each cluster center in the cluster center set, determine the target encoded information set and the target normalized information set corresponding to the cluster center; For each piece of encoded information in the encoded information set, determine the difference value between the encoded information and the corresponding target encoded information in the target encoded information set; For each normalized piece of information in the normalized information set, determine the distance value between the normalized piece of information and the target normalized piece of information in the target normalized information set; Based on the obtained set of difference values ​​and the obtained set of distance values, the historical user report information cluster to which the user report information belongs is determined.

4. The method according to claim 1, wherein, The step of determining the percentage of item value transfer ladder values ​​for the target user based on the percentage of each item value transfer ladder value included in the information submitted by at least one candidate historical user includes: The value transfer threshold percentages of each item are weighted and summed to generate a weighted sum value, which serves as the value transfer threshold percentage for the target user.

5. The method according to claim 1, wherein, The historical user-submitted information cluster is generated through the following steps: Retrieve the set of historical user-submitted information for the historical user set; Determine the number of cluster centers; The historical user-submitted information set is preprocessed to obtain the preprocessed historical user-submitted information set. Based on the number of cluster centers, the preprocessed historical user report information set is divided into clusters to obtain the preprocessed historical user report information cluster set. Generate a historical user report information cluster corresponding to the preprocessed historical user report information cluster.

6. The method according to claim 5, wherein, The step of dividing the preprocessed historical user-reported information set into clusters based on the number of cluster centers to obtain a preprocessed historical user-reported information cluster set includes: For every two preprocessed historical user reports in the preprocessed historical user report set, the two preprocessed historical user reports are input into the text similarity generation model to generate a similarity value for the two preprocessed historical user reports. For each preprocessed historical user report in the preprocessed historical user report set, perform the distance value determination step: Determine multiple similarity values ​​associated with the preprocessed historical user-submitted information; Determine the weighted average value corresponding to the plurality of similarity values; The weighted average value is determined as the distance value of the preprocessed historical user-submitted information; The obtained distance value set of the reported information is sorted to obtain the distance value sequence of the reported information; From the sequence of reported information distance values, the reported information distance values ​​whose differences between adjacent reported information distance values ​​meet the preset conditions are selected as target reported information distance values, resulting in multiple target reported information distance values. The number of target reported information distance values ​​included in the multiple target reported information distance values ​​is equal to the number of cluster centers. The multiple preprocessed historical user reports corresponding to the distance values ​​of the multiple target reports are determined as the cluster centers of each preprocessed historical user report cluster. Based on the cluster center of each preprocessed historical user report information cluster, the preprocessed historical user report information set is divided into clusters to obtain the preprocessed historical user report information cluster set.

7. The method according to claim 1, wherein, The method further includes: The percentage of the item value transfer tier for the target user is sent to the user display terminal corresponding to the target user.

8. An information generation device, comprising: The first acquisition unit is configured to acquire user-submitted information of the target user, wherein the target user is the user whose percentage of the value transfer ladder of the item is to be determined. The second acquisition unit is configured to acquire a pre-built set of historical user-reported information clusters, wherein each historical user-reported information cluster includes: the percentage of item value transfer ladder values. The first determining unit is configured to determine the historical user reporting information cluster to which the user reporting information belongs in the historical user reporting information cluster set, and use it as the target historical user reporting information cluster. The filtering unit is configured to filter out historical user submission information from the target historical user submission information cluster that has an information association relationship with the user submission information that meets a preset association condition, and use it as candidate historical user submission information to obtain at least one candidate historical user submission information. The second determining unit is configured to determine the percentage of item value transfer ladder values ​​for the target user based on the percentage of each item value transfer ladder value included in the information submitted by the at least one candidate historical user.

9. An electronic device, comprising: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

11. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-7.

Images