Information generation method, device, server, system and storage medium
By using the resource allocation model during the item allocation process, the allocation ratio is automatically determined based on the demand characteristic information of multiple ownership migration platforms, the problems of low allocation efficiency and inaccurate results in the existing technology are solved, and more reasonable and efficient are achieved item allocation.
Patent Information
- Application Number
- CN202011162735.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-10-27
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2040-10-27
AI Technical Summary
In the prior art, items in the online ownership migration platform are easily affected by experience differences among the configuration personnel, resulting in low distribution efficiency and unreasonable and accurate results.
By receiving the resource allocation request sent by the terminal, obtain the demand characteristic information of the target item on multiple ownership migration platforms, enter the resource allocation model to generate the allocation ratio, automatically determine the number of items on each platform, and reduce manual intervention.
It improves the rationality and accuracy of item distribution, reduces the influence of individual subjective factors, and improves the distribution efficiency.
Smart Images

Figure CN113762675B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to information processing technology, and in particular to an information generating method, device, server, system and storage medium. Background Art
[0002] With the vigorous development of e-commerce, people are more and more accustomed to creating item acquisition tasks online (such as online shopping). In response to this, various resource providers (such as merchants) have allocated the items they produce to various online ownership transfer platforms (such as various online shopping platforms), and used the various online ownership transfer platforms to transfer the ownership of items (such as selling items).
[0003] In the process of realizing the present invention, the inventors found that in the prior art, when allocating items to various ownership transfer platforms on the Internet, the configuration personnel usually need to rely on their own experience to determine the allocation quantity of each ownership transfer platform, and the experience of different configuration personnel varies greatly. The allocation process is easily affected by the configuration personnel's personal subjective factors, the allocation efficiency is low, and the allocation results are not reasonable and accurate. For example, it is easy for ownership transfer platforms with large demand (such as sales) to allocate too few quantities, resulting in insufficient inventory; while ownership transfer platforms with small demand may allocate too many quantities, resulting in excess inventory. Therefore, how to reasonably and accurately allocate items to various ownership transfer platforms is a technical problem that needs to be solved urgently. Summary of the invention
[0004] The embodiments of the present invention provide an information generation method, device, server, system and storage medium, which can make the allocation result more reasonable and accurate and improve the allocation efficiency.
[0005] In a first aspect, an embodiment of the present invention provides an information generation method, the method comprising:
[0006] A resource allocation request sent by a receiving terminal, wherein the resource allocation request includes identification information of a target item and quantity information to be allocated;
[0007] Obtaining demand characteristic information of the target item on at least two ownership transfer platforms according to the identification information, and inputting the demand characteristic information into a resource allocation model to generate a resource allocation ratio, wherein the resource allocation ratio includes the quantity allocation ratio of the target item on the at least two ownership transfer platforms;
[0008] Generate resource allocation information of the target item according to the resource allocation ratio and the information on the quantity to be allocated, wherein the resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms;
[0009] The resource allocation information is sent to the terminal.
[0010] In a second aspect, an embodiment of the present invention provides another information generation method, the method comprising:
[0011] receiving a resource allocation request sent by a terminal, wherein the resource allocation request includes identification information of a target item;
[0012] Obtaining demand characteristic information of the target item on at least two ownership transfer platforms according to the identification information, and inputting the demand characteristic information into a resource allocation model to generate a resource allocation ratio, wherein the resource allocation ratio includes the quantity allocation ratio of the target item on the at least two ownership transfer platforms;
[0013] The resource allocation ratio is sent to the terminal so that the terminal generates resource allocation information of the target item based on the resource allocation ratio and the information on the quantity to be allocated of the target item, wherein the resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms.
[0014] In a third aspect, an embodiment of the present invention provides an information generating device, the device comprising:
[0015] A first receiving module, configured to receive a resource allocation request sent by a terminal, wherein the resource allocation request includes identification information of a target item and information on the quantity to be allocated;
[0016] A first ratio generating module is used to obtain the demand characteristic information of the target item on at least two ownership transfer platforms according to the identification information, and input the demand characteristic information into a resource allocation model to generate a resource allocation ratio, wherein the resource allocation ratio includes the quantity allocation ratio of the target item on the at least two ownership transfer platforms;
[0017] An information generation module, configured to generate resource allocation information of the target item according to the resource allocation ratio and the information on the quantity to be allocated, wherein the resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms;
[0018] The first sending module is used to send the resource allocation information to the terminal.
[0019] In a fourth aspect, an embodiment of the present invention provides another information generating device, the device comprising:
[0020] A second receiving module, configured to receive a resource allocation request sent by a terminal, wherein the resource allocation request includes identification information of a target item;
[0021] A second ratio generating module is used to obtain the demand characteristic information of the target item on at least two ownership transfer platforms according to the identification information, and input the demand characteristic information into a resource allocation model to generate a resource allocation ratio, wherein the resource allocation ratio includes the quantity allocation ratio of the target item on the at least two ownership transfer platforms;
[0022] The second sending module is used to send the resource allocation ratio to the terminal, so that the terminal generates resource allocation information of the target item according to the resource allocation ratio and the information on the quantity to be allocated of the target item, and the resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms.
[0023] In a fifth aspect, an embodiment of the present invention provides a server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the information generation method as described in the first aspect or the second aspect of the embodiment of the present invention is implemented.
[0024] In a sixth aspect, an embodiment of the present invention provides an information generation system, comprising a server and a terminal for executing the information generation method as described in the first aspect or the second aspect of the embodiment of the present invention.
[0025] In a seventh aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the information generating method as described in the first aspect or the second aspect of the embodiment of the present invention.
[0026] In an embodiment of the present invention, when a resource allocation request is received from a terminal, the demand characteristic information of the target item on each ownership migration platform is input into a resource allocation model, and the resource allocation model is used to generate a resource allocation ratio of the target item. Then, the resource allocation information of the target item is generated according to the resource allocation ratio and the information on the quantity to be allocated of the target item. The resource allocation information includes the quantity of the target item allocated to each ownership migration platform. That is, in an embodiment of the present invention, the resource allocation model can be used to automatically determine the allocated quantity of the target item on each ownership migration platform. When the target item needs to be allocated to each ownership migration platform, the configuration personnel can directly refer to the allocated quantity in the automatically generated resource allocation information. The configuration personnel no longer need to determine the allocated quantity of each ownership migration platform by themselves. Therefore, the entire allocation process no longer relies on the experience of the configuration personnel, and can avoid the influence of personal subjective factors. In addition, when generating the resource allocation information of the target item, the demand characteristic information of the target item on each ownership migration platform is taken into consideration, so that the allocation result can be more reasonable and accurate, and the allocation efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 It is a schematic diagram of an application scenario of the information generating method provided by an embodiment of the present invention.
[0028] Figure 2 It is a flowchart of the information generation method provided by an embodiment of the present invention.
[0029] Figure 3 It is a schematic diagram of a training method of a resource allocation model provided in an embodiment of the present invention.
[0030] Figure 4 It is another flowchart of the information generating method provided by an embodiment of the present invention.
[0031] Figure 5 It is another flowchart of the information generating method provided by an embodiment of the present invention.
[0032] Figure 6 It is a structural schematic diagram of an information generating device provided by an embodiment of the present invention.
[0033] Figure 7 It is another structural schematic diagram of the information generating device provided by an embodiment of the present invention.
[0034] Figure 8 It is a structural diagram of an information generation system provided by an embodiment of the present invention.
[0035] Fig. 9 It is a structural diagram of a server provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0036] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
[0037] Since the item allocation method provided by the prior art relies on the manual allocation of the allocation personnel through their experience, the allocation efficiency is low. Moreover, since the manual allocation is easily affected by the subjective factors of the allocation personnel, the allocation result is not reasonable and accurate enough.
[0038] In view of this, an embodiment of the present invention provides an information generation method, which can automatically realize item allocation. A specific application scenario of the information generation method provided by the embodiment of the present invention can be as follows: Figure 1As shown, it includes a terminal and a server. When the target item needs to be allocated, the configuration personnel can send a resource allocation request to the server through the terminal. The resource allocation request may include the identification information of the target item and the quantity information to be allocated. The identification information may include the name, code, model and other information of the target item; the server receives the resource allocation request sent by the terminal, obtains the demand characteristic information of the target item on at least two ownership migration platforms, and inputs the obtained demand characteristic information into the resource allocation model to generate a resource allocation ratio. The resource allocation ratio includes the quantity allocation ratio of the target item on at least two ownership migration platforms. The ownership migration platform can be, for example, an online shopping platform, such as JD.com, Tmall, Pinduoduo and other online shopping platforms; the server generates resource allocation information of the target item according to the resource allocation ratio and the quantity information to be allocated. The resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms, and sends the resource allocation information to the terminal.
[0039] When the terminal receives the resource allocation information, it can display the resource allocation information on a preset interface. The configuration personnel can directly allocate the target items to each ownership transfer platform according to the allocation quantity in the automatically generated resource allocation information. The configuration personnel no longer need to determine the allocation quantity of each ownership transfer platform by themselves. Therefore, the entire allocation process no longer relies on the experience of the configuration personnel, and can avoid the influence of personal subjective factors. In addition, when generating the resource allocation information of the target item, the demand characteristic information of the target item on each ownership transfer platform is taken into consideration, so that the allocation result can be more reasonable and accurate, and the allocation efficiency is improved.
[0040] Figure 2 This is a flow chart of the information generation method provided in the embodiment of the present invention. The method can be executed by the information generation device provided in the embodiment of the present invention. The device can be implemented in software and / or hardware. In a specific embodiment, the device can be integrated in a server. The following embodiments will be described by taking the device integrated in a server as an example. Figure 2 , the method may specifically include the following steps:
[0041] Step 201: receiving a resource allocation request sent by a terminal, wherein the resource allocation request includes identification information of a target item and information on the quantity to be allocated.
[0042] Specifically, the target items include any items that can be transferred, such as clothing, stationery, food, electrical appliances, etc. The identification information of the target items may include the name, code, model, etc. of the target items, and the information on the quantity to be allocated includes the quantity to be allocated of the target items, which is at least 2.
[0043] In a specific implementation, when it is necessary to allocate the target item to each ownership transfer platform, the configuration personnel (such as a merchant) can send a resource allocation request to the server through the terminal, and the server receives the resource allocation request sent by the terminal. In an embodiment of the present invention, the ownership transfer platform can be an online shopping platform, such as Tmall, JD.com, Pinduoduo, etc. For example, for example, a mobile phone manufacturer has produced 60 mobile phones A, and these 60 mobile phones A need to be sold on the three platforms of Tmall, JD.com, and Pinduoduo. Then, a resource allocation request can be sent to the server through the terminal, and the identification information included in the resource allocation request can be: mobile phone A, and the quantity information to be allocated included in the resource allocation request can be: 60.
[0044] Step 202, obtaining demand characteristic information of the target item on at least two ownership migration platforms based on the identification information, and inputting the demand characteristic information into a resource allocation model to generate a resource allocation ratio, which includes the quantity allocation ratio of the target item on at least two ownership migration platforms.
[0045] For example, ownership transfer records (such as sales records) and user operation records (such as user clicks, favorites, adding to shopping carts, reservation records, etc.) related to the target items generated within a preset time period in the past can be collected from each ownership transfer platform. Based on the ownership transfer records and user operation records related to the target items, the demand characteristic information of the target items on each ownership transfer platform within the preset time period in the past can be obtained. The preset time period can be one month, two months, etc., and the demand characteristic information can be composed of multiple characteristic information.
[0046] In a specific embodiment, if there are M ownership transfer platforms, and each demand feature information includes N feature information, the demand feature information of the target item on these N platforms can be obtained as shown in Table 1 below, where x MN Indicates the Nth feature information of the target item obtained on the Mth ownership transfer platform:
[0047] Ownership transfer platform Demand characteristic information Platform 1 <![CDATA[x 11 ,x 12 ,x 13 ……x 1N ]]> Platform 2 <![CDATA[x 21 ,x 22 ,x 23 ……x 2N ]]> Platform 3 <![CDATA[x 31 ,x 32 ,x 33 ……x 3N ]]> …… …… Platform M <![CDATA[x M1 ,x M2 ,x M3 ……x MN ]]>
[0048] Table 1
[0049] For example, a specific demand characteristic information may be shown in Table 2 below:
[0050] The demand for the target item on the ownership transfer platform (e.g. sales volume) The click-through rate of the target item on the ownership transfer platform (e.g., sales click-through rate) The click ratio of the target item's resource provider (e.g. merchant) on the ownership transfer platform The click ratio of the category of the target item on the ownership transfer platform Number of clicks on the shopping cart of the target item on the ownership transfer platform Number of clicks on the target item's favorites on the ownership transfer platform The target item's scheduled quantity on the ownership transfer platform
[0051] Table 2
[0052] It should be noted that the characteristic information shown in Table 2 is only for illustration and does not constitute a limitation on the actual content and quantity of characteristic information.
[0053] In an embodiment of the present invention, a resource allocation model can be obtained by training samples in advance. For example, a large number of items that have been allocated can be used as preset items, and the demand feature information of the preset items on at least two ownership transfer platforms can be collected to construct samples, wherein the demand feature information of a preset item on at least two ownership transfer platforms constitutes a sample; the samples and the actual allocation ratio of the samples (i.e., the sample labels) are used as training data to perform model training to obtain a resource allocation model. The resource allocation model can be implemented using algorithms such as machine learning and deep learning, which are not specifically limited here.
[0054] The demand characteristic information of preset items on at least two ownership transfer platforms may be the same in quantity and type as the demand characteristic information of the target item on at least two ownership transfer platforms, and its specific collection method may also be the same as the collection method of the demand characteristic information of the target item on at least two ownership transfer platforms, which will not be repeated here.
[0055] Continuing with the above example, for example, if the resource allocation request is to allocate 60 mobile phones A to the three platforms of Tmall, JD.com, and Pinduoduo, the resource allocation ratio generated here can be the quantity allocation ratio of these 60 mobile phones on these three platforms, such as 1:2:3.
[0056] Step 203: Generate resource allocation information of the target item according to the resource allocation ratio and the information on the quantity to be allocated. The resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms.
[0057] Continuing with the above example, assuming that there are 60 mobile phones A to be allocated, and the resource allocation ratio generated for the three platforms of Tmall, JD.com, and Pinduoduo is 1:2:3, then the resource allocation information includes 10 mobile phones A allocated to Tmall, 20 mobile phones A allocated to JD.com, and 30 mobile phones A allocated to Pinduoduo.
[0058] In a specific implementation, when generating resource allocation information of a target item, the stock information of the target item on each ownership transfer platform may also be considered to further improve the rationality and accuracy of the allocation result. That is, when there is stock of the target item on any ownership transfer platform, the method for generating resource allocation information may further include the following steps:
[0059] (1) Obtaining inventory information of the target item on each of at least two ownership transfer platforms.
[0060] Among them, the inventory information includes the inventory of the target items on the corresponding ownership transfer platform.
[0061] (2) Determine the total amount to be allocated based on the inventory information and the amount to be allocated.
[0062] The total allocation amount information includes the total allocation amount of the target item, and the total allocation amount of the target item = the number of target items to be allocated + the stock of the target items in each ownership transfer platform.
[0063] (3) Generate resource allocation information based on the total allocation information and resource allocation ratio.
[0064] For example, there are 60 mobile phones A to be distributed among Tmall, JD.com, and Pinduoduo. There are 3 mobile phones A in stock on JD.com and Tmall, that is, the sum of the stocks on each platform is 6. The total number of mobile phones A distributed is 66. Assuming that the resource allocation ratio generated by the resource allocation model for these three platforms is 1:2:3, the number of mobile phones A distributed to Tmall is That is, 8 mobile phones A are allocated to Tmall; the number of mobile phones A allocated to JD.com is That is, 19 mobile phones A are allocated to JD.com; the number of mobile phones A allocated to Pinduoduo is That is, 33 mobile phones A are allocated to Tmall.
[0065] Step 204: Send the resource allocation information to the terminal.
[0066] When the terminal receives the resource allocation information, it can display the resource allocation information on a preset interface. The configuration personnel can directly allocate the target items to each ownership transfer platform according to the allocation quantity in the automatically generated resource allocation information. The configuration personnel no longer need to determine the allocation quantity of each ownership transfer platform by themselves. Therefore, the entire allocation process no longer relies on the experience of the configuration personnel, and can avoid the influence of personal subjective factors. In addition, when generating the resource allocation information of the target item, the demand characteristic information of the target item on each ownership transfer platform is taken into consideration, so that the allocation result can be more reasonable and accurate, and the allocation efficiency is improved.
[0067] In the above embodiment, one resource allocation model is used by default. In practical applications, in order to further improve the rationality and accuracy of the allocation result, multiple resource allocation models can be used. That is, there can be at least two resource allocation models. Then, at least two resource allocation models can be used according to Figure 3 The method shown is trained to obtain Figure 3 As shown, the model training method includes the following steps:
[0068] Step 301, collect demand characteristic information of preset items on at least two ownership transfer platforms to construct a sample.
[0069] For example, a large number of items that have been allocated can be used as preset items, and the demand characteristic information of the preset items on at least two ownership transfer platforms can be collected to construct a sample, wherein the demand characteristic information of one preset item on at least two ownership transfer platforms constitutes one sample. The demand characteristic information of the preset items on at least two ownership transfer platforms can be the same as the quantity and type of information contained in the demand characteristic information of the target item on at least two ownership transfer platforms, and its specific collection method can also be the same as the collection method of the demand characteristic information of the target item on at least two ownership transfer platforms, which will not be repeated here.
[0070] Step 302: Obtain at least two configured decision rules from the terminal.
[0071] The decision rule can be configured by the user on a preset interface of the terminal, and the server can obtain at least two configured decision rules from the terminal, where the decision rule is a basis or standard set by the user for allocating preset items.
[0072] Step 303: Use the samples and the actual allocation ratio of the samples under each of the at least two decision rules as training data to perform model training to obtain at least two resource allocation models.
[0073] In the specific implementation, the same sample can have different actual allocation ratios under different decision rules. For example, the actual allocation ratio of a sample under the first decision rule is 1:2:3, while the actual allocation ratio of the sample under the second decision rule is 2:1:2. That is, the actual allocation ratio of the sample under each decision rule can be used as the sample label of the corresponding sample, and the model training is performed in an output-oriented manner to obtain at least two resource allocation models.
[0074] For example, there are three configuration decision rules, namely, radical allocation rule, conservative allocation rule and general allocation rule. Among them, the radical allocation rule refers to the allocation of items according to the maximum sales volume. The higher the sales volume, the more items are allocated to the ownership migration platform; the conservative allocation rule refers to the allocation of items according to the minimum inventory backlog. The smaller the inventory backlog, the more items are allocated to the ownership migration platform; and the general allocation rule refers to the comprehensive consideration of sales volume and inventory. The greater the sales volume and the smaller the inventory, the more items are allocated to the ownership migration platform.
[0075] Then we can obtain the actual allocation ratio of each sample under these three decision rules respectively, and use each sample and the actual allocation ratio of the sample under these three rules as training data for model training, and we can get radical allocation rule model, conservative allocation rule model and general allocation rule model.
[0076] The following will take the resource allocation model including three (i.e., the first allocation model, the second allocation model, and the third allocation model) as an example to illustrate the information generation method provided by the embodiment of the present invention, wherein the three resource allocation models can be the radical allocation rule model, the conservative allocation rule model, and the general allocation rule model described above, respectively. Figure 4 As shown, the method comprises the following steps:
[0077] Step 401: receiving a resource allocation request sent by a terminal.
[0078] The resource allocation request includes the identification information of the target item and the quantity information to be allocated. The target item includes any item that can be transferred, such as clothing, stationery, food, electrical appliances, etc. The identification information of the target item may include the name, code, model, etc. of the target item, and the quantity information to be allocated includes the quantity to be allocated of the target item, which is at least 2.
[0079] In a specific implementation, when it is necessary to allocate the target item to each ownership transfer platform, the configuration personnel (such as a merchant) can send a resource allocation request to the server through the terminal, and the server receives the resource allocation request sent by the terminal. In an embodiment of the present invention, the ownership transfer platform can be an online shopping platform, such as Tmall, JD.com, Pinduoduo, etc.
[0080] Step 402, obtain the demand characteristic information of the target item on at least two ownership transfer platforms, and input the demand characteristic information into the first allocation model, the second allocation model and the third allocation model to generate the first allocation ratio, the second allocation ratio and the third allocation ratio.
[0081] For example, ownership transfer records (such as sales records) and user operation records (such as user clicks, favorites, adding to shopping carts, reservation records, etc.) related to the target items generated within a preset time period in the past can be collected from each ownership transfer platform. Based on the ownership transfer records and user operation records related to the target items, the demand characteristic information of the target items on each ownership transfer platform within the preset time period in the past can be obtained. The preset time period can be one month, two months, etc.
[0082] Since the first allocation model, the second allocation model and the third allocation model are resource allocation models corresponding to different decision rules, the generated first allocation ratio, second allocation ratio and third allocation ratio will also be different.
[0083] Step 403, determine the users who need the target item.
[0084] The demand users include users who have initiated item acquisition tasks for the target item (i.e., users who have purchased the target item) and users who have not initiated item acquisition tasks for the target item but have potential demand for the target item (i.e., users who have not purchased the target item but have potential shopping demand for the target item).
[0085] Specifically, the user operation records of registered users of each ownership transfer platform can be obtained, and the users who need the target item can be determined based on the user operation records of each ownership transfer platform. For example, if it is known from the user operation records that a registered user on a certain ownership transfer platform has purchased the target item, or collected the target item, or added the target item to the shopping cart, or reserved the target item, or browsed the target item, then the registered user can be determined as the user who needs the target item.
[0086] Step 404 , calculating the demand score of the demand user according to the characteristic information of the demand user, and determining the demand user whose demand score is higher than the preset score as the preset user.
[0087] By way of example, the characteristic information of the demand user may include multiple characteristic information. The characteristic information of the demand user may be obtained based on the user's registration information, historical transaction information, etc. on the ownership transfer platform. For example, the user's age, gender, delivery address, etc. may be obtained based on the user's registration information on the ownership transfer platform. The user's shopping frequency, annual consumption expenditure, single consumption expenditure, purchased item categories, etc. may be obtained based on the user's historical transaction information on the ownership transfer platform. The user's age, gender, delivery address, shopping frequency, annual consumption expenditure, single consumption expenditure, and purchased item categories are used as the user's characteristic information.
[0088] When calculating the demand score of the demand user based on the characteristic information of the demand user, the characteristic information of the demand user can be normalized to obtain the normalized value, and the characteristic weight pre-configured for each characteristic information can be obtained. The normalized value of each characteristic information of the demand user is multiplied by the corresponding characteristic weight and then summed to obtain the demand score of the user. For example, the weights configured for each characteristic information of the demand user can be: gender weight is 10> age weight is 9> shopping frequency weight is 8> annual consumption expenditure weight is 7> single consumption expenditure weight is 6> delivery address weight is 5> commodity category weight is 4.
[0089] In a specific embodiment, the demand score of the demand user can be calculated according to the following formula:
[0090]
[0091] Among them, P represents the amount of information contained in the characteristic information of the demand user, and w irepresents the feature weight of the i-th feature information, v i Represents the normalized value of the i-th feature information.
[0092] After obtaining the demand score of each demand user, the demand user with a demand score higher than the preset score can be selected and the selected demand user can be determined as the preset user. The demand score can reflect the purchase conversion rate of the demand user. Generally speaking, the purchase conversion rate of the demand user with a demand score higher than the preset score will be higher than that of the demand user with a demand score lower than the preset score.
[0093] Step 405: monitor the quantity of target items demanded by preset users.
[0094] By determining preset users, the number of monitored users can be reduced and data processing efficiency can be improved.
[0095] Step 406, calculating the demand ratio of the target item on at least two ownership transfer platforms according to the preset user demand quantity for the target item.
[0096] For example, the purchase of target items by preset users can be monitored, and the sales volume of each ownership transfer platform can be counted based on the purchase of target items by preset users. The demand ratio (i.e., sales ratio) of at least two ownership transfer platforms can be obtained based on the sales volume of each ownership transfer platform.
[0097] For example, within the preset time period, all preset users purchased 4 mobile phones A on Tmall, 10 mobile phones A on JD.com, and 2 mobile phones A on Pinduoduo. The demand ratio of these three platforms is 2:5:1.
[0098] In addition, after obtaining the number of preset user demands for the target item, the demand number can be clustered and the abnormal demand numbers can be eliminated to avoid interference from abnormal data. For example, a clustering graph can be generated based on the demand number, and discrete points in the clustering graph can be eliminated. After eliminating the abnormal demand numbers, the remaining demand numbers are used to calculate the demand ratio of the target item on at least two ownership transfer platforms.
[0099] Step 407: Obtain model weights of the first allocation model, the second allocation model, and the third allocation model according to the demand ratio.
[0100] For example, the corresponding model weight can be pre-configured for each demand ratio. Then, when the current demand ratio is obtained, the model weight corresponding to the demand ratio can be directly obtained to obtain the model weights of the first allocation model, the second allocation model and the third allocation model.
[0101] For another example, after obtaining the demand ratio, the difference of the demand ratio can be calculated, and the model weights of the first allocation model, the second allocation model, and the third allocation model can be configured in real time according to the difference. For example, if the difference is greater than the first preset value, the first allocation model is configured with a higher model weight, and the other two models are configured with lower model weights. If the difference is less than the second preset value, the second allocation model is configured with a higher model weight, and the other two models are configured with lower model weights. Among them, the first preset value is greater than the second preset value, and the specific configuration method can be determined according to actual needs.
[0102] In addition, for example, the ownership migration platform with the greatest demand can be determined according to the demand ratio, and the model weights pre-configured for the first allocation model, the second allocation model, and the third allocation model can be obtained according to the ownership migration platform with the greatest demand. For example, when the ownership migration platform with the greatest demand is the first ownership migration platform, the model weight corresponding to the first ownership migration platform configured in advance is obtained, thereby obtaining the model weights of the three models; if the ownership migration platform with the greatest demand is the second ownership migration platform, the model weight corresponding to the second ownership migration platform configured in advance is obtained, thereby obtaining the model weights of the three models. The specific configuration method can be determined according to actual needs.
[0103] In practical applications, instead of obtaining the model weights of the first allocation model, the second allocation model, and the third allocation model according to the demand ratio, the model weights of the first allocation model, the second allocation model, and the third allocation model that are pre-configured can be directly obtained. For example, the model weights are pre-configured for the three models, and after the output data of the three models are obtained, the model weights pre-configured for the three models are directly used.
[0104] Step 408, multiplying the model weights of the three resource allocation models by the resource allocation ratios generated by the corresponding resource allocation models and then summing them up to obtain the comprehensive allocation ratio of the target item.
[0105] For example, the comprehensive distribution ratio of the target item can be calculated according to the following formula:
[0106]
[0107] Where Q represents the number of resource allocation models, θ j represents the model weight of the j-th resource allocation model, y j Represents the resource allocation ratio generated by the j-th resource allocation model.
[0108] In a specific implementation, when there are multiple resource allocation models, it is also possible not to obtain the model weight of each resource allocation model, but to directly take the average of the resource allocation ratios generated by each resource allocation model, and use the average as the comprehensive allocation ratio of the target item.
[0109] Step 409: Generate resource allocation information of the target item according to the comprehensive allocation ratio and the quantity information to be allocated.
[0110] For instance, taking the allocation of 60 mobile phones A to Tmall, JD.com, and Pinduoduo as an example, if the comprehensive allocation ratio obtained by the three resource allocation ratios generated by the three resource allocation models is 2:1:3, then the resource allocation information includes 20 mobile phones A allocated to Tmall, 10 mobile phones A allocated to JD.com, and 30 mobile phones A allocated to Pinduoduo.
[0111] In a specific implementation, when generating resource allocation information of a target item, the stock information of the target item on each ownership transfer platform may also be considered to further improve the rationality of the allocation result. That is, when there is stock of the target item on any ownership transfer platform, the method for generating resource allocation information may further include the following steps:
[0112] Obtaining inventory information of the target item on each of the at least two ownership transfer platforms; wherein the inventory information includes the inventory of the target item on the corresponding ownership transfer platform;
[0113] Determine the total amount of allocation information according to the inventory information and the amount to be allocated information; wherein the total amount of allocation information includes the total amount of allocation of the target item, and the total amount of allocation of the target item = the amount to be allocated of the target item + the inventory of the target item on each ownership transfer platform;
[0114] Generate resource allocation information based on the total allocation information and the resource allocation ratio.
[0115] Step 410: Send the resource allocation information to the terminal.
[0116] When the terminal receives the resource allocation information, it can display the resource allocation information on a preset interface. The configuration personnel can directly allocate the target items to each ownership transfer platform according to the allocation quantity in the automatically generated resource allocation information. The configuration personnel no longer need to determine the allocation quantity of each ownership transfer platform by themselves. Therefore, the entire allocation process no longer relies on the experience of the configuration personnel, and can avoid the influence of personal subjective factors. In addition, when generating the resource allocation information of the target item, the demand characteristic information of the target item on each ownership transfer platform is taken into consideration, so that the allocation result can be more reasonable and accurate, and the allocation efficiency is improved.
[0117] The above embodiment describes a method for generating resource configuration information directly by a server. In practical applications, the server may also only provide resource allocation ratios to the terminal, and the terminal may generate resource configuration information by itself, that is, Figure 5 As shown, the information generation method provided by the embodiment of the present invention can also be as follows:
[0118] Step 501: receiving a resource allocation request sent by a terminal, wherein the resource allocation request includes identification information of a target item.
[0119] In the specific implementation, when it is necessary to allocate the target items to various ownership transfer platforms, the configuration personnel (such as merchants) can send a resource allocation request to the server through the terminal, and the server receives the resource allocation request sent by the terminal. Among them, the target items include any items that can be transferred, such as clothing, stationery, food, electrical appliances, etc. The identification information of the target items may include the name, code, model, etc. of the target items. The ownership transfer platform can be an online shopping platform, such as Tmall, JD.com, Pinduoduo, etc.
[0120] Step 502, obtaining demand characteristic information of the target item on at least two ownership migration platforms based on the identification information, and inputting the demand characteristic information into a resource allocation model to generate a resource allocation ratio, which includes the quantity allocation ratio of the target item on at least two ownership migration platforms.
[0121] For example, ownership transfer records (such as sales records) and user operation records (such as user clicks, favorites, adding to shopping carts, reservation records, etc.) related to the target items generated within a preset time period in the past can be collected from each ownership transfer platform. Based on the ownership transfer records and user operation records related to the target items, the demand characteristic information of the target items on each ownership transfer platform within the preset time period in the past can be obtained. The preset time period can be one month, two months, etc.
[0122] In an embodiment of the present invention, a resource allocation model can be obtained by training samples in advance. For example, a large number of items that have been allocated can be used as preset items, and the demand feature information of the preset items on at least two ownership transfer platforms can be collected to construct samples, wherein the demand feature information of a target item on at least two ownership transfer platforms constitutes a sample; the samples and the actual allocation ratio of the samples (i.e., the sample labels) are used as training data to perform model training to obtain a resource allocation model. The resource allocation model can be implemented using algorithms such as machine learning and deep learning, which are not specifically limited here.
[0123] The demand characteristic information of preset items on at least two ownership transfer platforms may be the same in quantity and type as the demand characteristic information of the target item on at least two ownership transfer platforms, and its specific collection method may also be the same as the collection method of the demand characteristic information of the target item on at least two ownership transfer platforms, which will not be repeated here.
[0124] Step 503, sending the resource allocation ratio to the terminal so that the terminal generates resource allocation information of the target item based on the resource allocation ratio and the quantity information of the target item to be allocated, and the resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms.
[0125] The information on the number of items to be allocated includes the number of target items to be allocated, which is at least 2. For example, the resource allocation request is to allocate mobile phone A to Tmall, JD.com, and Pinduoduo. The resource allocation ratio of mobile phone A generated by the server is 1:2:3, and the number of mobile phone A to be allocated is 60. The resource allocation information generated by the terminal may include 10 mobile phones A allocated to Tmall, 20 mobile phones A allocated to JD.com, and 30 mobile phones A allocated to Pinduoduo.
[0126] In a specific implementation, when generating resource allocation information of a target item, the terminal may also consider the stock information of the target item on each ownership transfer platform to further improve the rationality of the allocation result. That is, when there is stock of the target item on any ownership transfer platform, the method for generating resource allocation information by the terminal may include the following steps:
[0127] (1) Obtaining inventory information of the target item on each of at least two ownership transfer platforms from a server; wherein the inventory information includes the inventory of the target item on the corresponding ownership transfer platform.
[0128] (2) Determine the total amount of allocation information based on the inventory information and the amount to be allocated information; wherein the total amount of allocation information includes the total amount of allocation of the target item, and the total amount of allocation of the target item = the amount to be allocated of the target item + the inventory of the target item on each ownership transfer platform.
[0129] (3) Generate resource allocation information based on the total allocation information and resource allocation ratio.
[0130] In a specific embodiment, the server side can also use multiple resource allocation models to generate multiple resource allocation ratios for the target item, and combine the multiple resource allocation ratios to obtain the comprehensive allocation ratio of the target item, so as to further improve the rationality and accuracy of resource allocation; for example, the server can combine the model weights of multiple resource allocation models and the resource allocation ratio generated by the corresponding resource allocation model, multiply the model weights of multiple resource allocation models by the resource allocation ratio generated by the corresponding resource allocation model, and then sum them to obtain the comprehensive allocation ratio of the target item. In step 503, the comprehensive allocation ratio can be sent to the terminal, and the terminal can generate the resource allocation information of the target item according to the comprehensive allocation ratio and the information on the quantity to be allocated of the target item. For the specific weight acquisition method and related implementation details, please refer to the description of the previous embodiment, which will not be repeated here.
[0131] After the terminal generates the resource allocation information, it can display the resource allocation information on a preset interface. The configuration personnel can directly allocate the target items to each ownership transfer platform according to the allocation quantity in the automatically generated resource allocation information. The configuration personnel no longer need to determine the allocation quantity of each ownership transfer platform by themselves. Therefore, the entire allocation process no longer relies on the experience of the configuration personnel, and can avoid the influence of personal subjective factors. In addition, when generating the resource allocation information of the target item, the demand characteristic information of the target item on each ownership transfer platform is taken into consideration, so that the allocation result can be more reasonable and accurate, and the allocation efficiency is improved.
[0132] Figure 6 FIG. 1 is a structural diagram of an information generating device provided by an embodiment of the present invention, and the device is suitable for executing the information generating method provided by an embodiment of the present invention. Figure 6 As shown, the device may specifically include:
[0133] A first receiving module 601 is used to receive a resource allocation request sent by a terminal, wherein the resource allocation request includes identification information of a target item and information on the quantity to be allocated;
[0134] A first ratio generating module 602 is configured to obtain demand characteristic information of the target item on at least two ownership migration platforms according to the identification information, and input the demand characteristic information into a resource allocation model to generate a resource allocation ratio, wherein the resource allocation ratio includes a quantity allocation ratio of the target item on the at least two ownership migration platforms;
[0135] An information generation module 603 is used to generate resource allocation information of the target item according to the resource allocation ratio and the information on the quantity to be allocated, wherein the resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms;
[0136] The first sending module 604 is configured to send the resource allocation information to the terminal.
[0137] In one embodiment, the device further comprises a model training module;
[0138] The model training module is used to collect the demand characteristic information of preset items on the at least two ownership transfer platforms to construct samples; use the samples and the actual allocation ratio of the samples as training data to perform model training to obtain the resource allocation model.
[0139] In one embodiment, the resource allocation model includes at least two. Before the sample and the actual allocation ratio of the sample are used as training data to perform model training to obtain the resource allocation model, the model training module is further used to:
[0140] Obtaining at least two decision rules configured from the terminal;
[0141] The model training module uses the samples and the actual allocation ratios of the samples as training data to perform model training to obtain the resource allocation model, including:
[0142] The model training module uses the sample and the actual allocation ratio of the sample under each of the at least two decision rules as training data to perform model training to obtain the at least two resource allocation models.
[0143] In one embodiment, the resource allocation model includes at least two, and the first ratio generation module 602 inputs the demand characteristic information into the resource allocation model to generate a resource allocation ratio, including:
[0144] The first ratio generating module 602 inputs the demand characteristic information into each resource allocation model of the at least two resource allocation models to generate at least two resource allocation ratios;
[0145] The information generation module 603 generates the resource allocation information of the target item according to the resource allocation ratio and the information on the quantity to be allocated, including:
[0146] The information generation module 603 generates the resource allocation information of the target item according to the at least two resource allocation ratios and the to-be-allocated quantity information.
[0147] In one embodiment, the information generation module 603 generates the resource allocation information of the target item according to the at least two resource allocation ratios and the to-be-allocated quantity information, including:
[0148] The information generation module 603 obtains the model weight of each resource allocation model in the at least two resource allocation models; and generates the resource allocation information of the target item according to the model weight, the at least two resource allocation ratios and the information on the quantity to be allocated.
[0149] In one embodiment, the information generation module 603 obtains the model weight of each resource allocation model in the at least two resource allocation models, including:
[0150] The information generation module 603 calculates the demand ratio of the target item on the at least two ownership transfer platforms; and obtains the model weight of each resource allocation model in the at least two resource allocation models according to the demand ratio.
[0151] In one embodiment, the information generation module 603 calculates the demand ratio of the target item on the at least two ownership transfer platforms, including:
[0152] The information generation module 603 determines a preset user and monitors the quantity of demand for the target item by the preset user; and calculates the demand ratio of the target item on the at least two ownership transfer platforms according to the quantity of demand for the target item by the preset user.
[0153] In one embodiment, the information generating module 603 determines the preset user, including:
[0154] The information generation module 603 determines the users who need the target item, and the users who need the target item include users who have initiated item acquisition tasks for the target item and users who have not initiated item acquisition tasks for the target item but have potential needs for the target item; calculates the demand scores of the users according to the characteristic information of the users, and determines the users whose demand scores are higher than a preset score as the preset users.
[0155] In one embodiment, the information generation module 603 generates the resource allocation information of the target item according to the model weight, the at least two resource allocation ratios and the to-be-allocated quantity information, including:
[0156] The information generation module 603 multiplies the model weight of each resource allocation model in the at least two resource allocation models by the resource allocation ratio generated by the corresponding resource allocation model and then sums them to obtain the comprehensive allocation ratio of the target item; and generates the resource allocation information of the target item according to the comprehensive allocation ratio and the quantity information to be allocated.
[0157] In one embodiment, the information generation module 603 generates the resource allocation information of the target item according to the resource allocation ratio and the to-be-allocated quantity information, including:
[0158] The information generation module 603 obtains the inventory information of the target item on each of the at least two ownership migration platforms; determines the total allocation amount information based on the inventory information and the quantity to be allocated information; and generates the resource allocation information based on the total allocation amount information and the resource allocation ratio.
[0159] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0160] When the device of the embodiment of the present invention receives the resource allocation request from the terminal, it inputs the demand characteristic information of the target item on each ownership migration platform into the resource allocation model, generates the resource allocation ratio of the target item by using the resource allocation model, and then generates the resource allocation information of the target item according to the resource allocation ratio and the information on the quantity to be allocated of the target item. The resource allocation information includes the quantity of the target item allocated to each ownership migration platform, that is, the device of the embodiment of the present invention can automatically determine the allocated quantity of the target item on each ownership migration platform by using the resource allocation model. When the target item needs to be allocated to each ownership migration platform, the configuration personnel can directly refer to the allocated quantity in the automatically generated resource allocation information, and the configuration personnel no longer need to determine the allocated quantity of each ownership migration platform by themselves. Therefore, the entire allocation process no longer relies on the experience of the configuration personnel, and can avoid the influence of personal subjective factors. In addition, when generating the resource allocation information of the target item, the demand characteristic information of the target item on each ownership migration platform is taken into consideration, so that the allocation result can be more reasonable and accurate, and the allocation efficiency is improved.
[0161] Figure 7 FIG. 1 is another structural diagram of an information generating device provided by an embodiment of the present invention, and the device is suitable for executing the information generating method provided by an embodiment of the present invention. Figure 7 As shown, the device may specifically include:
[0162] The second receiving module 701 is used to receive a resource allocation request sent by a terminal, wherein the resource allocation request includes identification information of a target item;
[0163] A second ratio generating module 702 is configured to obtain demand characteristic information of the target item on at least two ownership migration platforms according to the identification information, and input the demand characteristic information into a resource allocation model to generate a resource allocation ratio, wherein the resource allocation ratio includes a quantity allocation ratio of the target item on the at least two ownership migration platforms;
[0164] The second sending module 703 is used to send the resource allocation ratio to the terminal, so that the terminal generates resource allocation information of the target item based on the resource allocation ratio and the information on the number of target items to be allocated, and the resource allocation information includes the number of the target items allocated to each of the at least two ownership migration platforms.
[0165] The device of the embodiment of the present invention, upon receiving a resource allocation request from a terminal, inputs the demand characteristic information of the target item on each ownership migration platform into a resource allocation model, generates a resource allocation ratio of the target item using the resource allocation model, and then sends the resource allocation ratio to the terminal, so that the terminal generates resource allocation information of the target item based on the resource allocation ratio and the information on the quantity to be allocated of the target item, wherein the resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms, that is, in the embodiment of the present invention, the resource allocation model can be used to automatically determine the allocated quantity of the target item on each ownership migration platform, and when the target item needs to be allocated to each ownership migration platform, the configuration personnel can directly refer to the allocated quantity in the automatically generated resource allocation information, and the configuration personnel no longer need to determine the allocated quantity of each ownership migration platform by themselves, so that the entire allocation process no longer relies on the experience of the configuration personnel, and can avoid the influence of personal subjective factors, and when generating the resource allocation information of the target item, the demand characteristic information of the target item on each ownership migration platform is taken into consideration, so that the allocation result can be more reasonable and accurate, and the allocation efficiency is improved.
[0166] The embodiment of the present invention also provides an information generation system, such as Figure 8 As shown, it includes a server 801 and a terminal 802 for executing the information generation method provided by the embodiment of the present invention. The specific implementation process can refer to the description of the previous embodiment and will not be repeated here.
[0167] Fig. 9 A structural diagram of a server provided in an embodiment of the present invention, Fig. 9 A block diagram of an exemplary server 912 suitable for use in implementing embodiments of the present invention is shown. Fig. 9 The server 912 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0168] like Fig. 9 As shown, the server 912 is in the form of a general-purpose computing device. The components of the server 912 may include, but are not limited to: one or more processors or processing units 916, a system memory 928, and a bus 918 connecting different system components (including the system memory 928 and the processing unit 916).
[0169] Bus 918 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.
[0170] The server 912 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the server 912, including volatile and non-volatile media, removable and non-removable media.
[0171] System memory 928 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 930 and / or cache memory 932. Server 912 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 934 may be used to read and write non-removable, non-volatile magnetic media ( Fig. 9 not shown, usually called a "hard drive"). Although Fig. 9 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical medium) may be provided. In these cases, each drive may be connected to bus 918 via one or more data medium interfaces. Memory 928 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of various embodiments of the present invention.
[0172] A program / utility 940 having a set (at least one) of program modules 942 may be stored, for example, in the memory 928. Such program modules 942 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 942 generally perform the functions and / or methods of the embodiments described herein.
[0173] The server 912 may also communicate with one or more external devices 914 (e.g., keyboards, pointing devices, displays 924, etc.), one or more devices that enable a user to interact with the server 912, and / or any device that enables the server 912 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 922. Furthermore, the device 912 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 920. As shown, the network adapter 920 communicates with the other modules of the device 912 via a bus 918. It should be understood that although Fig. 9 Not shown, other hardware and / or software modules may be used in conjunction with server 912, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0174] The processing unit 916 executes various functional applications and data processing by running the programs stored in the system memory 928, for example, implementing the information generation method provided in the embodiment of the present invention:
[0175] That is, when the processing unit 916 executes the program, it achieves: receiving a resource allocation request sent by a terminal, the resource allocation request including identification information of the target item and quantity information to be allocated; acquiring demand characteristic information of the target item on at least two ownership migration platforms based on the identification information, and inputting the demand characteristic information into a resource allocation model to generate a resource allocation ratio, the resource allocation ratio including the quantity allocation ratio of the target item on the at least two ownership migration platforms; generating resource allocation information of the target item based on the resource allocation ratio and the quantity information to be allocated, the resource allocation information including the quantity of the target item allocated to each of the at least two ownership migration platforms; and sending the resource allocation information to the terminal.
[0176] Of course, those skilled in the art can understand that the processing unit can also implement the information generating method provided by any embodiment of the present invention.
[0177] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the information generation method provided in all the embodiments of the present invention is implemented:
[0178] That is, when the program is executed by the processor, it is implemented as follows: receiving a resource allocation request sent by a terminal, the resource allocation request including identification information of the target item and quantity information to be allocated; acquiring demand characteristic information of the target item on at least two ownership migration platforms based on the identification information, and inputting the demand characteristic information into a resource allocation model to generate a resource allocation ratio, the resource allocation ratio including the quantity allocation ratio of the target item on the at least two ownership migration platforms; generating resource allocation information of the target item based on the resource allocation ratio and the quantity information to be allocated, the resource allocation information including the quantity of the target item allocated to each of the at least two ownership migration platforms; and sending the resource allocation information to the terminal.
[0179] Of course, the computer-readable storage medium provided by the embodiment of the present invention stores a computer program which is not limited to the method operations described above, but can also perform operations related to the information generation method provided by the embodiment of the present invention.
[0180] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.
[0181] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0182] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0183] Computer program code for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0184] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. A method for generating information, characterized in that: include: A resource allocation request sent by a receiving terminal, wherein the resource allocation request includes identification information of a target item and quantity information to be allocated; Obtain demand characteristic information of the target item on at least two ownership transfer platforms according to the identification information, and input the demand characteristic information into a resource allocation model to generate a resource allocation ratio, wherein the resource allocation ratio includes the quantity allocation ratio of the target item on the at least two ownership transfer platforms, and the resource allocation model is obtained by taking the demand characteristic information of the items that have been allocated on at least two ownership transfer platforms as samples, taking the samples and the actual allocation ratio of the samples under the decision rule as training data, and performing model training; Generate resource allocation information of the target item according to the resource allocation ratio and the information on the quantity to be allocated, wherein the resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms; The resource allocation information is sent to the terminal.
2. The information generation method according to claim 1, characterized in that: The resource allocation model includes at least two parts, and before taking the sample and the actual allocation ratio of the sample under the decision rule as training data and performing model training, it also includes: Obtaining at least two decision rules configured from the terminal; The method of using the samples and the actual distribution ratio of the samples under the decision rule as training data and performing model training includes: The samples and the actual allocation ratio of the samples under each of the at least two decision rules are used as training data to perform model training to obtain the at least two resource allocation models.
3. The information generation method according to claim 1, characterized in that: The resource allocation model includes at least two, and the step of inputting the demand characteristic information into the resource allocation model to generate a resource allocation ratio includes: Inputting the demand characteristic information into each resource allocation model of the at least two resource allocation models to generate at least two resource allocation ratios; The generating the resource allocation information of the target item according to the resource allocation ratio and the to-be-allocated quantity information includes: The resource allocation information of the target item is generated according to the at least two resource allocation ratios and the to-be-allocated quantity information.
4. The information generation method according to claim 3, characterized in that: The generating the resource allocation information of the target item according to the at least two resource allocation ratios and the to-be-allocated quantity information includes: Obtaining a model weight of each resource allocation model in the at least two resource allocation models; The resource allocation information of the target item is generated according to the model weight, the at least two resource allocation ratios and the to-be-allocated quantity information.
5. The information generation method according to claim 4, characterized in that: The obtaining of the model weight of each resource allocation model in the at least two resource allocation models comprises: Calculate the demand ratio of the target item on the at least two ownership transfer platforms; A model weight of each resource allocation model in the at least two resource allocation models is obtained according to the demand ratio.
6. The information generating method according to claim 5, characterized in that: The calculating the demand ratio of the target item on the at least two ownership transfer platforms includes: Determine a preset user and monitor the quantity of demand for the target item by the preset user; According to the demand quantity of the preset user for the target item, the demand ratio of the target item on the at least two ownership transfer platforms is calculated.
7. The information generating method according to claim 6, characterized in that: The determining of the preset user includes: Determine users who have demand for the target item, wherein the users who have demand for the target item include users who have initiated item acquisition tasks for the target item and users who have not initiated item acquisition tasks for the target item but have potential demand for the target item; The demand score of the demand user is calculated according to the characteristic information of the demand user, and the demand user whose demand score is higher than a preset score is determined as the preset user.
8. The information generating method according to claim 4, characterized in that: The generating the resource allocation information of the target item according to the model weight, the at least two resource allocation ratios and the to-be-allocated quantity information includes: The model weight of each resource allocation model in the at least two resource allocation models is multiplied by the resource allocation ratio generated by the corresponding resource allocation model, and then the sum is calculated to obtain the comprehensive allocation ratio of the target item; The resource allocation information of the target item is generated according to the comprehensive allocation ratio and the quantity information to be allocated.
9. The information generating method according to claim 1, characterized in that: The generating the resource allocation information of the target item according to the resource allocation ratio and the to-be-allocated quantity information includes: Acquiring inventory information of the target item on each of the at least two ownership transfer platforms; Determine the total amount of allocation information according to the inventory information and the amount to be allocated information; The resource allocation information is generated according to the total allocation information and the resource allocation ratio.
10. A method for generating information, characterized in that: include: receiving a resource allocation request sent by a terminal, wherein the resource allocation request includes identification information of a target item; Obtain demand characteristic information of the target item on at least two ownership transfer platforms according to the identification information, and input the demand characteristic information into a resource allocation model to generate a resource allocation ratio, wherein the resource allocation ratio includes the quantity allocation ratio of the target item on the at least two ownership transfer platforms, and the resource allocation model is obtained by taking the demand characteristic information of the items that have been allocated on at least two ownership transfer platforms as samples, taking the samples and the actual allocation ratio of the samples under the decision rule as training data, and performing model training; The resource allocation ratio is sent to the terminal so that the terminal generates resource allocation information of the target item based on the resource allocation ratio and the information on the quantity to be allocated of the target item, wherein the resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms.
11. An information generating device, characterized in that: include: A first receiving module, configured to receive a resource allocation request sent by a terminal, wherein the resource allocation request includes identification information of a target item and information on the quantity to be allocated; A first ratio generating module is used to obtain the demand characteristic information of the target item on at least two ownership transfer platforms according to the identification information, and input the demand characteristic information into a resource allocation model to generate a resource allocation ratio, wherein the resource allocation ratio includes the quantity allocation ratio of the target item on the at least two ownership transfer platforms, and the resource allocation model is obtained by using the demand characteristic information of the items that have been allocated on at least two ownership transfer platforms as samples, using the samples and the actual allocation ratio of the samples under the decision rule as training data, and performing model training; An information generation module, configured to generate resource allocation information of the target item according to the resource allocation ratio and the information on the quantity to be allocated, wherein the resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms; The first sending module is used to send the resource allocation information to the terminal.
12. An information generating device, characterized in that: include: A second receiving module, configured to receive a resource allocation request sent by a terminal, wherein the resource allocation request includes identification information of a target item; A second ratio generating module is used to obtain the demand characteristic information of the target item on at least two ownership transfer platforms according to the identification information, and input the demand characteristic information into a resource allocation model to generate a resource allocation ratio, wherein the resource allocation ratio includes the quantity allocation ratio of the target item on the at least two ownership transfer platforms, and the resource allocation model is obtained by taking the demand characteristic information of the items that have been allocated on at least two ownership transfer platforms as samples, taking the samples and the actual allocation ratio of the samples under the decision rule as training data, and performing model training; The second sending module is used to send the resource allocation ratio to the terminal, so that the terminal generates resource allocation information of the target item according to the resource allocation ratio and the information on the quantity to be allocated of the target item, and the resource allocation information includes the quantity of the target item allocated to each of the at least two ownership migration platforms.
13. A server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements the information generating method according to any one of claims 1 to 9, or executes the information generating method according to claim 10.
14. An information generation system, characterized in that: The system comprises a server and a terminal for executing the information generating method according to any one of claims 1 to 9, or comprises a server and a terminal for executing the information generating method according to claim 10.
15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the information generation method according to any one of claims 1 to 9 is implemented, or when the program is executed by a processor, the information generation method according to claim 10 is implemented.
