Information generation method, device, terminal, system and storage medium

Abstract

The embodiment of the present invention discloses an information generation method, device, equipment, system and storage medium, the method comprising: obtaining initial demand information of a target item from a server, the initial demand information is generated by the server using a demand prediction model to predict the demand of the target item; displaying the initial demand information and demand configuration information on a preset interface, and monitoring the adjustment operation of the initial demand information according to the demand configuration information on the preset interface; when the adjustment operation is monitored, generating the target demand information of the target item according to the adjustment operation. In the embodiment of the present invention, after obtaining the prediction result of the demand prediction of the target item using the model, a manual adjustment method will be provided through the preset interface, so that the model prediction result can be manually adjusted, combining the model prediction and manual adjustment, integrating the algorithm advantages and human wisdom, and improving the accuracy of the demand prediction result.

Description

Technical Field

[0001] The present invention relates to information processing technology, and in particular to an information generating method, device, terminal, system and storage medium. Background Art

[0002] In the field of e-commerce, it is very important to predict the demand (e.g., sales volume) of items, which affects various management tasks including planning, budgeting, inventory, replenishment, etc. In the process of realizing the present invention, the inventors found that the demand prediction methods provided by the prior art often have the technical problem that the prediction results are not accurate enough. Summary of the invention

[0003] Embodiments of the present invention provide an information generation method, device, terminal, system and storage medium, which can improve the accuracy of demand quantity prediction.

[0004] In a first aspect, an embodiment of the present invention provides an information generation method, the method comprising:

[0005] Acquire initial demand quantity information of a target item from a server, wherein the initial demand quantity information is generated by the server using a demand quantity prediction model to predict the demand quantity of the target item;

[0006] Displaying the initial demand information and demand configuration information on a preset interface, and monitoring an adjustment operation on the preset interface based on the demand configuration information on the initial demand information;

[0007] When the adjustment operation is monitored, target demand quantity information of the target item is generated according to the adjustment operation.

[0008] In a second aspect, an embodiment of the present invention provides an information generating device, the device comprising:

[0009] An acquisition module, used to acquire initial demand quantity information of a target item from a server, wherein the initial demand quantity information is generated by the server performing demand quantity prediction on the target item using a demand quantity prediction model;

[0010] A display module, used to display the initial demand information and demand configuration information on a preset interface, and monitor the adjustment operation of the initial demand information according to the demand configuration information on the preset interface;

[0011] A generating module is used to generate target demand quantity information of the target item according to the adjusting operation when the adjusting operation is detected.

[0012] In a third aspect, an embodiment of the present invention further provides a terminal, 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, an information generation method as described in any one of the embodiments of the present invention is implemented.

[0013] In a fourth aspect, an embodiment of the present invention further provides an information generation system, comprising a terminal and a server for executing any of the information generation methods described in the embodiments of the present invention.

[0014] In a fifth 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 an information generating method as described in any one of the embodiments of the present invention.

[0015] In the embodiment of the present invention, the initial demand information of the target item is obtained from the server. The initial demand information is generated by the server using the demand prediction model to predict the demand of the target item. The initial demand information and demand configuration information are displayed on the preset interface, and the adjustment operation of the initial demand information according to the demand configuration information on the preset interface is monitored; when the adjustment operation is detected, the target demand information of the target item is generated according to the adjustment operation. That is, in the embodiment of the present invention, after obtaining the prediction result of the demand prediction of the target item using the model, a manual adjustment method will be provided through the preset interface, so that the model prediction result can be manually adjusted, combining the model prediction and manual adjustment, integrating the algorithm advantages and human wisdom, and improving the accuracy of the demand prediction result. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of the information generation method provided by an embodiment of the present invention.

[0017] Figure 2 yes Figure 1 A flowchart of an embodiment of step 11 in FIG.

[0018] Figure 3 yes Figure 2 FIG. 1 is a flow chart of an embodiment of step 112 in FIG.

[0019] Figure 4 yes Figure 3 A flowchart of an embodiment of step 1123 in FIG.

[0020] Figure 5 yes Figure 1 A flowchart of an embodiment of step 12 in FIG.

[0021] Figure 6 yes Figure 5 A flowchart of an embodiment of step 123 in FIG.

[0022] Figure 7 It is a structural schematic diagram of an information generating device provided by an embodiment of the present invention.

[0023] Figure 8 It is a structural diagram of an information generation system provided by an embodiment of the present invention.

[0024] Fig. 9 It is a structural diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] 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.

[0026] The item demand forecasting methods provided by the prior art can generally be divided into two types: one is to rely on manual experience for forecasting. Due to the large differences in experience and strong subjectivity among forecasters, it is difficult to ensure the accuracy of the forecast results. The other is to rely on algorithm model forecasting, such as machine learning models, deep learning models, etc. This method relies on data-driven and has high requirements on the perfection of driving data. For the ever-changing item ownership transfer activities (such as promotional activities), the forecast results are also inaccurate due to the lack of effective driving data.

[0027] In view of this, an embodiment of the present invention provides an information generation method, which obtains the initial demand information of the target item from the server. The initial demand information is generated by the server using a demand prediction model to predict the demand of the target item, displays the initial demand information and demand configuration information on a preset interface, and monitors the adjustment operation of the initial demand information based on the demand configuration information on the preset interface; when the adjustment operation is detected, the target demand information of the target item is generated according to the adjustment operation. That is, in the embodiment of the present invention, after obtaining the prediction result of the demand prediction of the target item using the model, a manual adjustment method will be provided through the preset interface, so that the model prediction result can be manually adjusted, combining the model prediction and manual adjustment, integrating the algorithm advantages and human wisdom, and improving the accuracy of the demand prediction result.

[0028] Figure 1The present invention provides a flowchart of an information generation method provided in an embodiment of the present invention. The method can be executed by an information generation device provided in an 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 terminal. The terminal can be a computer device such as a tablet computer, a laptop computer, a desktop computer, etc. that has a storage unit and a microprocessor installed and has computing capabilities. The following embodiments will be described by taking the device integrated in a terminal as an example. Reference Figure 1 , the method may specifically include the following steps:

[0029] Step 11, obtaining initial demand quantity information of the target item from the server, wherein the initial demand quantity information is generated by the server by predicting the demand quantity of the target item using a demand quantity prediction model.

[0030] The target item may refer to the item that is planned to participate in this ownership transfer activity (such as this promotion activity). The target item may include items that have participated in historical ownership transfer activities (such as historical promotion activities) (which may be called old items) and items that have not participated in historical ownership transfer activities (which may be called new items). The demand prediction model may refer to a model implemented using a preset algorithm, such as a machine learning algorithm, a deep learning algorithm, a year-on-year algorithm, etc. The demand prediction model can be used to characterize the correspondence between the characteristic information of an item and the demand information of the item. Specifically, the terminal may send the configured active item list to the server. The active item list may include the identification information of the target item. The identification information of the target item may be, for example, name, model, etc. The server collects the characteristic information of the target item and inputs the characteristic information of the target item into the demand prediction model, so as to use the demand prediction model to predict the demand for the target item and generate the initial demand information of the target item. The terminal obtains the initial demand information of the target item from the server.

[0031] Step 12: display the initial demand information and demand configuration information on a preset interface, and monitor the adjustment operation of the initial demand information according to the demand configuration information on the preset interface.

[0032] The initial demand information of the target item may include the initial demand of the target item predicted by the demand prediction model. The initial demand may refer to the predicted demand of the target item on the day of this ownership transfer activity.

[0033] There may be multiple target items. When displaying the initial demand information, the initial demand information of each target item may be sorted in order from large to small according to the size of the initial demand included in the initial demand information of each target item, and the initial demand information of each target item may be displayed on a preset interface according to the sorting.

[0034] Furthermore, when displaying the initial demand information, the historical demand information of the target item can also be obtained from the server, and the demand comparison information of the target item is generated according to the initial demand information and historical demand information of the target item, and the demand comparison information of the target item is displayed on the preset interface.

[0035] For example, when the target item is a new product that has not participated in any historical ownership transfer activity, the historical demand information of the target item may include the daily average demand information of the target item within a preset number of days before the current ownership transfer activity (the daily average demand information includes the daily average demand). The preset number of days may be determined based on actual conditions, such as ten days, thirty days, etc., and is not specifically limited here. Then, based on the initial demand information of the target item and the daily average demand information of the target item within a preset number of days before the current ownership transfer activity, the month-on-month demand information of the target item may be generated. The month-on-month demand information includes a month-on-month demand value, where the month-on-month demand value = initial demand of the target item / average daily demand of the target item within a preset number of days before the current ownership transfer activity. The month-on-month demand information of each target item is then displayed in descending order according to the month-on-month demand value.

[0036] For example, when the target item is an old product that has participated in a historical ownership transfer activity, the historical demand information of the target item may include the target item's daily average demand information within a preset number of days before the current ownership transfer activity (the daily average demand information includes the daily average demand), the target item's demand information on the day of the historical ownership transfer activity (the demand information on that day includes the demand on that day), and the target item's daily average demand information within a preset number of days before the historical ownership transfer activity (the daily average demand information includes the daily average demand). Then, based on the target item's initial demand information and the target item's daily average demand information within a preset number of days before the current ownership transfer activity, the target item's month-on-month demand information may be generated. The month-on-month demand information includes the month-on-month demand value. The month-on-month value of quantity = initial demand for the target item / average daily demand for the target item within the preset number of days before this ownership transfer activity, and then the month-on-month demand information of each target item is sorted and displayed in descending order according to the month-on-month demand values; at the same time, the year-on-year demand information of the target item can also be generated according to the demand information of the target item on the day of the historical ownership transfer activity and the average daily demand information of the target item within the preset number of days before the historical ownership transfer activity, and the year-on-year demand information includes the year-on-year demand value, and the year-on-year demand value = demand for the target item on the day of the historical ownership transfer activity / average daily demand for the target item within the preset number of days before the historical ownership transfer activity, and then the year-on-year demand information of each target item is sorted and displayed in descending order according to the year-on-year demand values.

[0037] In a specific implementation, the demand configuration information (such as sales plan information) may include the total demand of all configured target items on the day of this ownership transfer activity (such as the planned sales volume on the day of this promotion activity). The terminal can sum the initial demand of all target items to generate an initial total demand, and display the initial total demand on a preset interface so that the user can know the difference between the initial total demand and the planned total demand on the day of this ownership transfer activity, and determine whether the initial demand information of the target item needs to be adjusted based on the difference.

[0038] Specifically, corresponding adjustment controls can be provided for each target item on the preset interface, for example, demand multiple modification controls, demand absolute value modification controls, etc. The user can determine whether adjustment is needed and which target items' initial demand information needs to be adjusted based on the information displayed on the preset interface. If the initial demand information of a target item needs to be adjusted, the adjustment control corresponding to the target item is triggered, and the terminal monitors the user's adjustment operation on the initial demand information on the preset interface.

[0039] Step 13: When the adjustment operation is detected, target demand quantity information of the target item is generated according to the adjustment operation.

[0040] For example, when the user learns from the information displayed on the preset interface that the total initial demand is less than the total demand on the day of the planned ownership transfer activity, the user can adjust the initial demand information of the target items with smaller initial demand, smaller month-on-month demand, or smaller year-on-year demand according to the sorting, such as increasing the initial demand of these target items so that the total initial demand is as equal to or slightly exceeds the total demand on the day of the planned ownership transfer activity. The terminal generates the target demand information of the target items based on the user's adjustment operation. In addition, if the total initial demand is not less than the total demand on the day of the planned ownership transfer activity, the initial demand of the target item does not need to be adjusted, and the initial demand information of the target item can be directly displayed as the final target demand information.

[0041] After the target demand information of the target item is generated, the target demand information of the target item can be displayed on the preset interface. In addition, the target demand information of the target item obtained by manually adjusting the demand can be highlighted to prompt the relevant business personnel to carry out targeted sales operations for these target items to ensure that the sales plan is finally achieved.

[0042] The above technical solution obtains the initial demand information of the target item from the server, displays the initial demand information and demand configuration information on the preset interface, and monitors the adjustment operation of the initial demand information according to the demand configuration information on the preset interface; when the adjustment operation is monitored, the target demand information of the target item is generated according to the adjustment operation, that is, after obtaining the prediction result of the demand prediction of the target item using the model, a manual adjustment method will be provided through the preset interface, so that the model prediction result can be manually adjusted, combining model prediction and manual adjustment, integrating the advantages of algorithm and human wisdom, improving the accuracy of demand prediction results, balancing the gap between demand and plan, and improving the usability of the prediction method.

[0043] In some embodiments, the server may use multiple demand prediction models to predict the demand of the target item, and the terminal may obtain the initial demand information of the target item based on the prediction results of the target item combined with the multiple demand prediction models. The multiple prediction models may be models implemented using different algorithms to improve the accuracy of model prediction. The following is an example of multiple demand prediction models including a first prediction model and a second prediction model. Figure 2 As shown, step 11 may specifically include the following steps:

[0044] Step 111, obtaining first demand information and second demand information of the target item from the server, wherein the first demand information is generated by the server using a first prediction model to predict the demand for the target item, and the second demand information is generated by the server using a second prediction model to predict the demand for the target item, and the first prediction model and the second prediction model are prediction models implemented using different algorithms.

[0045] Specifically, taking the first prediction model as a model implemented by machine learning, deep learning and other algorithms as an example, the first prediction model can be pre-trained by sample data, and the process of the server using the first prediction model to predict the demand for the target item can be as follows:

[0046] Characteristic information of the target item is collected, and the characteristic information of the target item is input into a first prediction model to generate first demand quantity information of the target item.

[0047] The characteristic information of the target object may include but is not limited to the following characteristics:

[0048] Demand characteristics: such as the demand for the target item on the day of the historical ownership transfer activity and the daily average demand and price before the historical ownership transfer activity, and the demand and price of the target item before this ownership transfer activity;

[0049] Attribute characteristics: such as the category, brand, function, origin, etc. of the target item;

[0050] Related features: such as weather conditions related to the target item, online public opinion index, traffic information, promotional plans of the target item, strategy classification, etc.

[0051] For example, taking the second prediction model as a model implemented by the same-year-on-year algorithm as an example, the process of using the second prediction model to predict the demand for the target item can be as follows:

[0052] (1) If the target item is an old item that has participated in a historical ownership transfer activity, the server can directly input the historical demand information of the target item into the second prediction model to generate the second demand information of the target item.

[0053] By way of example, the historical demand information of the target item may include the daily average demand S1 of the target item a preset number of days before the historical ownership transfer activity (for example, the daily average demand ten days or thirty days before the historical ownership transfer activity), the demand S2 of the target item on the day of the historical ownership transfer activity, and the daily average demand S3 of the target item a preset number of days before the current ownership transfer activity (for example, the daily average demand ten days or thirty days before the current ownership transfer activity).

[0054] When the server uses the second prediction model to predict the demand for the target item, it can first calculate the promotion factor F1 of the target item based on S1 and S2, F1=S2 / S1, then the predicted demand value of the target item R1=S3*F, that is, the second demand included in the second demand information is R1=S3*F, and the second demand may refer to the predicted demand value of the target item (old product) on the day of this ownership transfer activity predicted by the second prediction model.

[0055] (2) If the target item is a new product that has not participated in any historical ownership transfer activities, the server needs to first determine similar products of the target item and make a demand forecast for the target item based on the historical demand information of similar old products and the historical demand information of the target item. That is, the server needs to input the historical demand information of the target item and the historical demand information of similar products into a second forecasting model to generate second demand information for the target item.

[0056] Similar items to the target item are items that have participated in historical ownership transfer activities, that is, old items.

[0057] Specifically, the server can first use the feature information of the target item to construct a multi-dimensional feature vector of the target item, use the cosine similarity algorithm to calculate the similarity between the target item and each candidate old product, and then group the candidate old products according to brand category. In the group with the same brand category as the target item, select a preset number (such as 5, 10, etc.) of old products whose similarity with the target item is greater than a preset similarity threshold (such as 60%, 70%, etc.), and use the selected old products as similar products of the target item.

[0058] For example, if the brand of the target item is X and the category is mobile phones, then within the group of X-brand mobile phones, a preset number of X-brand mobile phones that have participated in historical ownership transfer activities and whose similarity with the target item is greater than a preset similarity threshold may be selected; if within the group of X-brand mobile phones, the number of X-brand mobile phones that have participated in historical ownership transfer activities is insufficient, then the brand may be not limited and the entire mobile phone group may be expanded to select mobile phones that have participated in historical ownership transfer activities and whose similarity with the target item is greater than a preset similarity threshold.

[0059] The above only uses the cosine similarity algorithm and groups by brand and category as an example to illustrate the method of determining similar products of the target item. In actual applications, other algorithms and other grouping methods can also be used to determine similar products of the target item, which are not specifically limited here.

[0060] In a specific implementation, when the target item is a new product, when the server uses the second prediction model to predict the demand for the target item, it can first calculate the promotion factor of each similar product according to the method provided above, and calculate the promotion factor of the new product based on the promotion factors of each similar product. For example, if there are N similar products selected, N is a positive integer, then the average of the promotion factors of the N similar products can be used as the promotion factor of the new product; or the promotion factors of the N similar products can be weighted and summed, and the resulting sum can be used as the promotion factor of the new product, which is not specifically limited here.

[0061] After obtaining the promotion factor of the new product, the demand for the new product can be predicted based on the promotion factor of the new product and the historical demand information of the new product. Since the new product is an item that has not participated in historical promotion activities, the historical demand information of the new product may only include the daily average demand S4 of the new product for a preset number of days before this ownership transfer activity. Assuming that the promotion factor of the new product calculated based on N similar products is F2, the demand forecast value of the new product is R2 = S4*F2, that is, the second demand included in the second demand information is R2 = S4*F2, and the second demand may refer to the demand forecast value of the target item (new product) on the day of this ownership transfer activity predicted by the second prediction model.

[0062] Step 112: Select the first demand information or the second demand information as initial demand information according to a preset selection rule.

[0063] The specific selection method can be as follows Figure 3 As shown, the following steps are included:

[0064] Step 1121 , obtaining from the server characteristic information of the target item that is input into the first prediction model by the server when the first prediction model is used to predict the demand of the target item.

[0065] Step 1122, displaying the characteristic information of the target object on a preset interface, and monitoring the completeness confirmation operation of the characteristic information of the target object on the preset interface.

[0066] Step 1123, when a completeness confirmation operation is monitored, the first demand information or the second demand information is selected as the initial demand information according to the confirmation result of the completeness confirmation operation indication.

[0067] Since the first prediction model is a model implemented by algorithms such as machine learning and deep learning, the prediction accuracy of the first prediction model depends on the completeness of the input feature information. If the input feature information is incomplete, the prediction result of the first prediction model will not be accurate enough. Therefore, confirmation of the completeness of the feature information is added here.

[0068] For example, a completeness confirmation control may be provided to the user in the preset interface of the terminal, so that the user can confirm whether the characteristic information of the target item input into the first prediction model is complete. For example, the terminal may display the characteristic information of the target item input into the first preset model obtained from the server in the preset interface, and the user may check the characteristic information. If it is found that the characteristic information contains a lack of promotional scheme, insufficient demand characteristic data, incomplete attribute characteristic information, etc., the user may submit a confirmation result of incomplete characteristic information to the terminal through the completeness confirmation control; conversely, if the characteristic information of the target item is complete, the user may submit a confirmation result of complete characteristic information to the terminal through the completeness confirmation control.

[0069] When the completeness confirmation result indicates that the characteristic information of the target item is complete, the terminal can select the first demand information as the initial demand information of the target item; conversely, when the completeness confirmation result indicates that the characteristic information of the target item is incomplete, the terminal can select the second demand information as the initial demand information of the target item.

[0070] In a specific embodiment, Figure 4 As shown, when the completeness confirmation result indicates that the characteristic information of the target item is incomplete, the terminal selects the second demand quantity information as the initial demand quantity information of the target item, which may specifically include:

[0071] Step 11231: whether the target item has participated in historical ownership transfer activities. If so, execute step 11232; otherwise, execute step 11233.

[0072] That is, when confirming whether the target item is a new product or an old product, if it is an old product, the second demand information generated by the first prediction of the demand for the target item can be directly generated using the second prediction model, and the second demand information generated by the first prediction can be used as the initial demand information of the target item.

[0073] Step 11232, selecting the second demand quantity information generated by the initial prediction as the initial demand quantity information of the target item.

[0074] Step 11233, obtaining from the server identification information of similar products of the target product used when the second prediction model is used to predict the demand of the target product for the first time.

[0075] When the target item is a new product, since the demand forecast result of the new product depends on the selection of similar products, if the selection of similar products is unreasonable, the prediction result of the second prediction model may not be accurate. Therefore, a step of confirming whether similar products need to be adjusted is added here to improve the accuracy of the prediction results.

[0076] Step 11234, displaying identification information of similar products on a preset interface, and monitoring adjustment operations on similar products on the preset interface.

[0077] For example, an adjustment confirmation control may be provided to the user on a preset interface displaying identification information of similar products, so that the user can confirm whether the similar products need to be adjusted. If adjustment is required, an adjustment interface is provided for the user to adjust the similar products, and the adjustment may include deleting one or some similar products used in the initial prediction, adding one or more similar products to the target product, replacing one or some similar products used in the initial prediction with other similar products selected by the user, etc. The terminal monitors the adjustment operation on the similar products on the preset interface.

[0078] Step 11235: Check whether adjustment operation on similar products is detected. If so, execute step 11236; otherwise, return to step 11232.

[0079] That is, if the user determines not to adjust the similar products of the target item, the terminal will not detect the adjustment operation on the similar products. The terminal can directly use the second demand information generated by the initial demand prediction of the target item using the second prediction model as the initial demand information of the target item.

[0080] Step 11236, obtaining the adjusted identification information of the similar products, and sending the adjusted identification information of the similar products to the server.

[0081] When the server receives the identification information of the adjusted similar product, it inputs the historical demand information of the target product and the adjusted historical demand information of the similar product into the second prediction model, and predicts and generates the second demand information of the target product again. The terminal obtains the second demand information generated by the second prediction from the server.

[0082] Step 11237, obtaining from the server second demand information generated by the server using the second prediction model to perform demand prediction on the target item again.

[0083] Step 11238, selecting the second demand quantity information generated by the re-prediction as the initial demand quantity information of the target item.

[0084] In a possible implementation scheme, if it is confirmed that the characteristic information of the target item is incomplete, an information completion control can be provided to the user in the preset interface of the terminal so that the user can manually complete the characteristic information of the target item. The terminal sends the completed characteristic information of the target item to the server, so that the server inputs the completed characteristic information of the target item into the first prediction model, and uses the first prediction model to predict the demand for the target item again. The terminal obtains the first demand information generated by the first prediction model from the server, and uses the first demand information generated by the first prediction model as the initial demand information of the target item.

[0085] In the above technical solution, by adding a step of manual confirmation of the completeness of feature information and a step of manual adjustment of similar products, the black box of the prediction model is opened, which makes it easier to add some manual information and additional information that is difficult to quantify into the prediction model, thereby improving the accuracy of the model's prediction.

[0086] In a possible implementation, when there are multiple demand forecasting models, the forecast result of the default forecasting model can also be set as the initial demand information of the target item. For example, the step of manually confirming the completeness of the feature information and the step of manually adjusting similar items can be omitted. The terminal directly uses the forecast result of a default forecasting model as the initial demand information of the target item. For example, the forecast result of the first forecasting model can be used as the initial demand information of the target item by default, which is not specifically limited here.

[0087] In some embodiments, the initial demand information may be further processed for display, such as Figure 5 As shown, step 12 may specifically include the following steps:

[0088] Step 121, obtaining historical demand information of the target item from the server.

[0089] Step 122: Generate target item demand comparison information based on the initial demand information and the historical demand information.

[0090] For example, when the target item is a new product that has not participated in any historical ownership transfer activities, the historical demand information of the target item may include the daily average demand information of the target item within a preset number of days before the current ownership transfer activity (the daily average demand information includes the daily average demand), and the preset number of days may be determined based on actual conditions, such as ten days, thirty days, etc., and is not specifically limited here. Based on the initial demand information of the target item and the daily average demand information of the target item within a preset number of days before the current ownership transfer activity, the month-on-month demand information of the target item may be generated. The month-on-month demand information includes a month-on-month demand value, and the month-on-month demand value = initial demand of the target item / daily average demand of the target item within a preset number of days before the current ownership transfer activity.

[0091] For example, when the target item is an old product that has participated in a historical ownership transfer activity, the historical demand information of the target item may include the daily average demand information of the target item within a preset number of days before the current ownership transfer activity (the daily average demand information includes the daily average demand), the demand information of the target item on the day of the historical ownership transfer activity (the demand information on that day includes the demand on that day), and the daily average demand information of the target item within a preset number of days before the historical ownership transfer activity (the daily average demand information includes the daily average demand). Then, based on the initial demand information of the target item and the daily average demand information of the target item within the preset number of days before the current ownership transfer activity, the month-on-month demand information of the target item can be generated. The month-on-month demand information includes the month-on-month demand value, which is: the month-on-month demand value = the initial demand of the target item / the average daily demand of the target item within the preset days before this ownership transfer activity; and then the month-on-month demand information of each target item is sorted and displayed in order from large to small according to the month-on-month demand value; at the same time, the year-on-year demand information of the target item can be generated according to the demand information of the target item on the day of the historical ownership transfer activity and the average daily demand information of the target item within the preset days before the historical ownership transfer activity. The year-on-year demand information includes the year-on-year demand value, which is: the year-on-year demand value = the demand of the target item on the day of the historical ownership transfer activity / the average daily demand of the target item within the preset days before the historical ownership transfer activity.

[0092] Step 123: Displaying the target item demand comparison information on a preset interface.

[0093] There can be multiple target items, and the specific display method can be as follows Figure 6As shown, the following steps are included:

[0094] Step 1231, sorting the demand quantity comparison information of each target item according to a preset sorting rule.

[0095] Step 1232: Display the demand comparison information of each target item on the preset interface according to the sorting result.

[0096] For example, when the target item is a new product, the generated demand comparison information is the month-on-month demand information, and the month-on-month demand information of each target item can be displayed in descending order according to the month-on-month demand values; when the target item is an old product, the generated demand comparison information includes the month-on-month demand information and the year-on-year demand information, and the month-on-month demand information of each target item can be displayed in descending order according to the month-on-month demand values, and the year-on-year demand information of each target item can be displayed in descending order according to the year-on-year demand values.

[0097] Figure 7 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 7 As shown, the device may specifically include:

[0098] An acquisition module 71 is used to acquire initial demand quantity information of a target item from a server, wherein the initial demand quantity information is generated by the server using a demand quantity prediction model to predict the demand quantity of the target item;

[0099] A display module 72, used to display the initial demand information and demand configuration information on a preset interface, and monitor the adjustment operation of the initial demand information according to the demand configuration information on the preset interface;

[0100] The generating module 73 is used to generate the target demand quantity information of the target item according to the adjusting operation when the adjusting operation is detected.

[0101] In one embodiment, the display module 72 displays the initial demand information on a preset interface, including:

[0102] Acquire historical demand information of the target item from the server;

[0103] Generate demand comparison information of the target item according to the initial demand information and the historical demand information;

[0104] The demand comparison information of the target item is displayed on the preset interface.

[0105] In one embodiment, when the target item has not participated in a historical ownership transfer activity, the historical demand information includes the daily average demand information of the target item within a preset number of days before the current ownership transfer activity. The display module 72 generates demand comparison information of the target item based on the initial demand information and the historical demand information, including:

[0106] The month-on-month demand information of the target item is generated based on the initial demand information and the daily average demand information of the target item within a preset number of days before the current ownership transfer activity.

[0107] In one embodiment, when the target item has participated in a historical ownership transfer activity, the historical demand information includes the target item's daily average demand information within a preset number of days before the current ownership transfer activity, the target item's demand information on the day of the historical ownership transfer activity, and the target item's daily average demand information within a preset number of days before the historical ownership transfer activity. The display module 72 generates demand comparison information of the target item based on the initial demand information and the target item's historical demand information, including:

[0108] Generate month-on-month demand information for the target item based on the initial demand information and the daily average demand information for the target item within a preset number of days before the ownership transfer activity;

[0109] According to the demand quantity information of the target item on the day of the historical ownership transfer activity and the daily average demand quantity information of the target item within a preset number of days before the historical ownership transfer activity, the year-on-year demand quantity information of the target item is generated.

[0110] In one embodiment, the target items include multiple items, and the display module 72 displays the demand comparison information of the target items on the preset interface, including:

[0111] Sort the demand comparison information of each target item according to the preset sorting rules;

[0112] The demand comparison information of each target item is displayed on the preset interface according to the sorting result.

[0113] In one embodiment, the acquisition module 71 acquires the initial demand quantity information of the target item from the server, including:

[0114] Acquire first demand quantity information and second demand quantity information of the target item from the server, wherein the first demand quantity information is generated by the server using a first prediction model to predict the demand quantity of the target item, and the second demand quantity information is generated by the server using a second prediction model to predict the demand quantity of the target item, and the first prediction model and the second prediction model are prediction models implemented using different algorithms;

[0115] The first demand quantity information or the second demand quantity information is selected as the initial demand quantity information according to a preset selection rule.

[0116] In one embodiment, the acquisition module 71 selects the first demand information or the second demand information as the initial demand information according to a preset selection rule, including:

[0117] Acquiring from the server the characteristic information of the target item input into the first prediction model by the server when predicting the demand quantity of the target item using the first prediction model;

[0118] Displaying the characteristic information of the target object on the preset interface, and monitoring the completeness confirmation operation of the characteristic information of the target object on the preset interface;

[0119] When the perfection confirmation operation is monitored, the first demand information or the second demand information is selected as the initial demand information according to the confirmation result indicated by the perfection confirmation operation.

[0120] In one embodiment, the acquisition module 71 selects the first demand information or the second demand information as the initial demand information according to the confirmation result of the completeness confirmation operation instruction, including:

[0121] When the completion confirmation result indicates that the characteristic information of the target item is complete, selecting the first demand quantity information as the initial demand quantity information;

[0122] When the completion confirmation result indicates that the characteristic information of the target item is incomplete, the second demand quantity information is selected as the initial demand quantity information.

[0123] In one embodiment, when the completeness confirmation result indicates that the characteristic information of the target item is incomplete, the acquisition module 71 selects the second demand quantity information as the initial demand quantity information, including:

[0124] When the completeness confirmation result indicates that the characteristic information of the target item is incomplete and the target item has participated in historical ownership transfer activities, the second demand quantity information is selected as the initial demand quantity information.

[0125] In one embodiment, when the completion confirmation result indicates that the characteristic information of the target item is incomplete, the acquisition module 71 selects the second demand quantity information as the initial demand quantity information, including:

[0126] When the completeness confirmation result indicates that the characteristic information of the target item is incomplete and the target item has not participated in a historical ownership transfer activity, obtaining from the server identification information of similar items of the target item used when the second prediction model is used to predict the demand for the target item for the first time, the similar items are items that have participated in the historical ownership transfer activity and whose similarity to the target item exceeds a preset similarity threshold;

[0127] Displaying identification information of the similar product on the preset interface, and monitoring adjustment operations on the similar product on the preset interface;

[0128] If no adjustment operation on the similar product is detected, the second demand quantity information generated by the initial prediction is selected as the initial demand quantity information;

[0129] If an adjustment operation on the similar product is monitored, the identification information of the adjusted similar product is obtained, and the identification information of the adjusted similar product is sent to the server, so that the server uses the second prediction model to predict the demand for the target item again, obtains the second demand information generated by the second prediction from the server, and selects the second demand information generated by the second prediction as the initial demand information.

[0130] 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.

[0131] The device of the embodiment of the present invention will obtain the initial demand information of the target item from the server. The initial demand information is generated by the server using the demand prediction model to predict the demand of the target item, and the initial demand information and demand configuration information are displayed on the preset interface, and the adjustment operation of the initial demand information according to the demand configuration information on the preset interface is monitored; when the adjustment operation is detected, the target demand information of the target item is generated according to the adjustment operation. That is, after obtaining the prediction result of the demand prediction of the target item using the model, the device of the embodiment of the present invention will provide a manual adjustment method through the preset interface, so that the model prediction result can be manually adjusted, combining the model prediction and manual adjustment, integrating the algorithm advantages and human wisdom, and improving the accuracy of the demand prediction result.

[0132] The embodiment of the present invention also provides an information generation system, such as Figure 8 As shown, it includes a terminal 81 and a server 82 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.

[0133] The information generation method provided by an embodiment of the present invention is described below with a specific example. For example, the target items include item A and item B, where item A is an old item that has participated in a historical ownership transfer activity, and item B is a new item that has not participated in a historical ownership transfer activity.

[0134] For item A, the server can input the characteristic information of item A into the first prediction model, use the first prediction model to predict the demand for it, and obtain first demand information A1; on the other hand, the historical demand information of item A is input into the second prediction model, and the demand for it is predicted using the second prediction model to obtain second demand information A2; the terminal obtains the first demand information A1 and the second demand information A2 from the server, and obtains the characteristic information of item A input into the first prediction model from the server, displays the characteristic information of item A, and monitors the user's confirmation result of the completeness of the characteristic information. If the confirmation result indicates that the characteristic information is complete, the terminal directly uses A1 as the initial demand information of item A. If it is incomplete, the terminal uses A2 as the initial demand information of item A.

[0135] For item B, the server can input the feature information of item B into the first prediction model, use the first prediction model to predict the demand for it, and obtain first demand information B1; on the other hand, the server determines N similar products of item B from the candidate old products through a preset similarity algorithm, inputs the historical demand information of item B and the historical demand information of N similar products into the second prediction model, uses the second prediction model to predict the demand for it, and obtains second demand information B2; the terminal obtains the first demand information B1 and the second demand information B2 from the server, and obtains the feature information of item B input into the first prediction model from the server, displays the feature information of item B, and monitors the user's confirmation result of the completeness of the feature information. If the confirmation result indicates that the feature information is complete, the terminal directly uses B1 as the item. If the initial demand information of item B is incomplete, the terminal obtains from the server the identification information of similar products of item B used by the server when using the second prediction model to predict the demand for item B and generate the second demand information B2, and displays the identification information of similar products for the user to confirm whether the similar products need to be adjusted. If not, the second demand information B2 is used as the initial demand information of item B. If the similar products need to be adjusted, the terminal obtains the identification information of the adjusted similar products, and sends the adjusted identification information of the similar products to the server, so that the server uses the second prediction model to predict the demand for the target item again and generate the second demand information B3. The terminal obtains the second demand information B3 generated by the second prediction from the server, and selects the second demand information B3 as the initial demand information of item B.

[0136] After obtaining the initial demand information of item A and item B, the initial demand information of item A and item B can be displayed. For example, for item A, year-on-year demand information and month-on-month demand information can be generated based on the initial demand information of item A and the historical demand information of item A. For item B, month-on-month demand information of item B can be generated based on the initial demand information of item B and the historical demand information of item B. Finally, the year-on-year demand information and month-on-month demand information of item A can be sorted and displayed in descending order of the quantity values ​​in the information, and the month-on-month demand information of item B can be displayed.

[0137] After the display, the user can use the displayed information to determine whether the initial demand information of item A and item B needs to be adjusted. For example, based on the displayed information, if the predicted total initial demand is much smaller than the planned total demand, the predicted initial demand needs to be adjusted. When making adjustments, some items can be selected for initial demand adjustment (for example, several items with lower initial demand and / or month-on-month demand values ​​are selected in order to make initial demand adjustments, or items with larger differences between year-on-year demand values ​​and month-on-month demand values ​​are selected to make initial demand adjustments, etc.), or initial demand adjustments can be made for all items, so that the predicted total initial demand is ultimately equal to or exceeds the planned total demand as much as possible.

[0138] Fig. 9 A structural diagram of a terminal provided by an embodiment of the present invention, Fig. 9 A block diagram of an exemplary terminal 912 suitable for use in implementing embodiments of the present invention is shown. Fig. 9 The terminal 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.

[0139] like Fig. 9 As shown, the terminal 912 is in the form of a general-purpose computing device. The components of the terminal 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).

[0140] 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.

[0141] Terminal 912 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by terminal 912, including volatile and non-volatile media, removable and non-removable media.

[0142] 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. Terminal 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. 9not 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.

[0143] 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.

[0144] The terminal 912 may also communicate with one or more external devices 914 (e.g., keyboards, pointing devices, displays 924, etc.), may communicate with one or more devices that enable a user to interact with the terminal 912, and / or may communicate with any device that enables the terminal 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 terminal 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.

[0145] 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:

[0146] That is, when the processing unit 916 executes the program, it achieves: obtaining initial demand information of the target item from the server, the initial demand information is generated by the server using a demand prediction model to predict the demand for the target item; displaying the initial demand information and demand configuration information on a preset interface, and monitoring the adjustment operation of the initial demand information based on the demand configuration information on the preset interface; and when the adjustment operation is monitored, generating the target demand information of the target item based on the adjustment operation.

[0147] 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.

[0148] 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:

[0149] That is, when the program is executed by the processor, it is achieved: obtaining initial demand information of the target item from the server, the initial demand information is generated by the server using a demand prediction model to predict the demand for the target item; displaying the initial demand information and demand configuration information on a preset interface, and monitoring the adjustment operation of the initial demand information based on the demand configuration information on the preset interface; when the adjustment operation is monitored, generating the target demand information of the target item according to the adjustment operation.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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: Acquiring initial demand information of a target item from a server, including: acquiring first demand information and second demand information of the target item from the server, acquiring from the server characteristic information of the target item input into the first prediction model by the server when performing demand prediction for the target item using the first prediction model; displaying the characteristic information of the target item on a preset interface, and monitoring a completeness confirmation operation of the characteristic information of the target item on the preset interface; selecting the first demand information as the initial demand information when the completeness confirmation operation is monitored and the confirmation result indicated by the completeness confirmation operation is that the characteristic information of the target item is complete, and selecting the second demand information as the initial demand information when the completeness confirmation result indicates that the characteristic information of the target item is incomplete; The first demand information is generated by the server using a first prediction model to predict the demand for the target item, and the second demand information is generated by the server using a second prediction model to predict the demand for the target item. The first prediction model is a model implemented by a machine learning or deep learning algorithm. The input data of the first prediction model includes feature information of the target item. The second prediction model is a model implemented by a year-on-year algorithm. The input data of the second prediction model includes a promotion factor of the target item. The promotion factor F1 of the target item is determined based on the daily average demand S1 of the target item in a preset number of days before the historical ownership transfer activity and the demand S2 of the target item on the day of the historical ownership transfer activity. F1=S2 / S1. Or the promotion factor of the target item is determined based on the promotion factor of a similar item of the target item, and the promotion factor of the similar item is the ratio of the demand for the similar item on the day of the historical ownership transfer activity to the average daily demand for the similar item in a preset number of days before the historical ownership transfer activity; Acquire historical demand information of the target item from the server; Generate demand comparison information of the target item according to the initial demand information and the historical demand information; Displaying the target item's demand quantity comparison information and demand quantity configuration information on a preset interface, and monitoring the user's adjustment operation on the initial demand quantity information according to the demand quantity configuration information on the preset interface; When the adjustment operation is monitored, target demand quantity information of the target item is generated according to the adjustment operation.

2. The information generation method according to claim 1, characterized in that: When the target item has not participated in a historical ownership transfer activity, the historical demand information includes the daily average demand information of the target item within a preset number of days before the current ownership transfer activity. The demand comparison information of the target item is generated based on the initial demand information and the historical demand information, including: The month-on-month demand information of the target item is generated based on the initial demand information and the daily average demand information of the target item within a preset number of days before the current ownership transfer activity.

3. The information generation method according to claim 1, characterized in that: When the target item has participated in a historical ownership transfer activity, the historical demand information includes the average daily demand information of the target item within a preset number of days before the current ownership transfer activity, the demand information of the target item on the day of the historical ownership transfer activity, and the average daily demand information of the target item within a preset number of days before the historical ownership transfer activity. The demand comparison information of the target item is generated based on the initial demand information and the historical demand information of the target item, including: Generate month-on-month demand information for the target item based on the initial demand information and the daily average demand information for the target item within a preset number of days before the ownership transfer activity; According to the demand quantity information of the target item on the day of the historical ownership transfer activity and the daily average demand quantity information of the target item within a preset number of days before the historical ownership transfer activity, the year-on-year demand quantity information of the target item is generated.

4. The information generation method according to claim 1, characterized in that: The target items include multiple items, and the displaying of the demand comparison information of the target items on the preset interface includes: Sort the demand comparison information of each target item according to the preset sorting rules; The demand comparison information of each target item is displayed on the preset interface according to the sorting result.

5. The information generation method according to claim 1, characterized in that: When the completion confirmation result indicates that the characteristic information of the target item is incomplete, selecting the second demand quantity information as the initial demand quantity information includes: When the completeness confirmation result indicates that the characteristic information of the target item is incomplete and the target item has participated in historical ownership transfer activities, the second demand quantity information is selected as the initial demand quantity information.

6. The information generating method according to claim 1, characterized in that: When the completion confirmation result indicates that the characteristic information of the target item is incomplete, selecting the second demand quantity information as the initial demand quantity information includes: When the completeness confirmation result indicates that the characteristic information of the target item is incomplete and the target item has not participated in a historical ownership transfer activity, obtaining from the server identification information of similar items of the target item used when the second prediction model is used to predict the demand for the target item for the first time, the similar items are items that have participated in the historical ownership transfer activity and whose similarity to the target item exceeds a preset similarity threshold; Displaying identification information of the similar product on the preset interface, and monitoring adjustment operations on the similar product on the preset interface; If no adjustment operation on the similar product is detected, the second demand quantity information generated by the initial prediction is selected as the initial demand quantity information; If an adjustment operation on the similar product is monitored, the identification information of the adjusted similar product is obtained, and the identification information of the adjusted similar product is sent to the server, so that the server uses the second prediction model to predict the demand for the target item again, obtains the second demand information generated by the second prediction from the server, and selects the second demand information generated by the second prediction as the initial demand information.

7. An information generating device, characterized in that: include: An acquisition module, used to acquire initial demand information of a target item from a server, including: acquiring first demand information and second demand information of the target item from the server, acquiring from the server characteristic information of the target item input into the first prediction model by the server when predicting the demand of the target item using the first prediction model; displaying the characteristic information of the target item on a preset interface, and monitoring a completeness confirmation operation of the characteristic information of the target item on the preset interface; when the completeness confirmation operation is monitored and the confirmation result indicated by the completeness confirmation operation is that the characteristic information of the target item is complete, selecting the first demand information as the initial demand information, and when the completeness confirmation result indicates that the characteristic information of the target item is incomplete, selecting the second demand information as the initial demand information; wherein the first demand information is the demand information of the target item by the server using the first prediction model The second demand quantity information is generated by the server using a second prediction model to predict the demand quantity of the target item, the first prediction model is a model implemented by a machine learning or deep learning algorithm, the input data of the first prediction model includes feature information of the target item, the second prediction model is a model implemented by a year-on-year algorithm, the input data of the second prediction model includes a promotion factor of the target item, the promotion factor F1 of the target item is determined based on the daily average demand quantity S1 of the target item in a preset number of days before the historical ownership transfer activity and the demand quantity S2 of the target item on the day of the historical ownership transfer activity, F1=S2 / S1, or the promotion factor of the target item is determined based on the promotion factor of a similar product of the target item, the promotion factor of the similar product is the ratio of the demand quantity of the similar product on the day of the historical ownership transfer activity to the daily average demand quantity of the similar product in the preset number of days before the historical ownership transfer activity; A display module, configured to obtain the historical demand information of the target item from the server; and generate demand comparison information of the target item according to the initial demand information and the historical demand information; Displaying the target item's demand quantity comparison information and demand quantity configuration information on a preset interface, and monitoring the user's adjustment operation on the initial demand quantity information according to the demand quantity configuration information on the preset interface; A generating module is used to generate target demand quantity information of the target item according to the adjusting operation when the adjusting operation is detected.

8. A terminal 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, the information generating method according to any one of claims 1 to 6 is implemented.

9. An information generation system, characterized in that: The invention comprises a terminal and a server for executing the information generating method as claimed in any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the information generating method according to any one of claims 1 to 6 is implemented.

Images