CN113762996B - Information generation method, device and storage medium - Google Patents
Information generation method, device and storage medium Download PDFInfo
- Publication number
- CN113762996B CN113762996B CN202010560519.0A CN202010560519A CN113762996B CN 113762996 B CN113762996 B CN 113762996B CN 202010560519 A CN202010560519 A CN 202010560519A CN 113762996 B CN113762996 B CN 113762996B
- Authority
- CN
- China
- Prior art keywords
- value
- value attribute
- early warning
- attribute value
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000008859 change Effects 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 abstract description 17
- 230000005856 abnormality Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 14
- 230000000694 effects Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000001737 promoting effect Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000007474 system interaction Effects 0.000 description 2
- 230000001550 time effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0213—Consumer transaction fees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0222—During e-commerce, i.e. online transactions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0235—Discounts or incentives, e.g. coupons or rebates constrained by time limit or expiration date
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method, a device and a storage medium for generating information, which are characterized in that firstly, a first value attribute value of a target object is obtained, value attribute information meeting preset conditions is obtained, the first value attribute value and the value attribute information are input into a pre-trained actual value attribute value prediction model matched with the first value attribute value of the target object to generate an actual value attribute value of the target object, then the first value attribute value and the value attribute information are input into a pre-trained early warning value attribute value prediction model matched with the first value attribute value of the target object to generate an early warning value attribute value corresponding to the target object, and finally, when the actual value attribute value is lower than the early warning value attribute value, early warning information is generated. According to the embodiment of the application, the actual value attribute value and the early warning value attribute value of the target object are used for identifying the target object with the abnormal actual value attribute value and prompting, so that the efficiency and the accuracy of abnormality identification are improved.
Description
Technical Field
The present application relates to the field of electronic commerce technologies, and in particular, to a method, an apparatus, and a storage medium for generating information.
Background
With the increasing maturity of the electronic commerce industry, sales promotion for goods is increasing. Wherein, the sales promotion of commodity price and class is changed frequently, if the setting personnel of each sales promotion are different, the superposition of multiple sales promotion can cause abnormal sales promotion. When the sales promotion system, the commodity system and the coupon system are relatively independent, if the sales promotion system, the commodity system and the coupon system are related to a plurality of commodities, the superposition condition of the sales promotion is complex, the mutual influence among the systems cannot be known in real time, the abnormality cannot be identified manually, and the abnormality can be found only when the sales promotion is effective.
Disclosure of Invention
The embodiment of the application provides an information generation method, which solves the problem that the actual value attribute value of a target object cannot be identified when the actual value attribute value of the target object is abnormal, and improves the identification efficiency and the identification accuracy when the actual value attribute value of the target object is abnormal.
The method comprises the following steps:
acquiring a first value attribute value of a target object;
Acquiring value attribute information meeting preset conditions, wherein the preset conditions are that a first time range carried by the value attribute information contains a time point representing the current time;
Inputting the first value attribute value and the value attribute information into a pre-trained actual value attribute value prediction model matched with the first value attribute value of the target object to generate an actual value attribute value of the target object, wherein the actual value attribute value prediction model is used for representing the change relation of the first value attribute value of the target object after the condition of applying the actual value attribute value;
Inputting the first value attribute value and the value attribute information into a pre-trained early warning value attribute value prediction model matched with the first value attribute value of the target object to generate an early warning value attribute value corresponding to the target object, wherein the early warning value attribute value prediction model is used for representing the corresponding relation between the first value attribute value and the early warning value attribute value of the target object;
and comparing the actual value attribute value with the early warning value attribute value, and generating early warning information when the actual value attribute value is lower than the early warning value attribute value.
Optionally, in the actual value attribute prediction model, the value attribute information is applied to the first value attribute value of the target item, and the actual value attribute value of the target item is calculated based on the value attribute information.
Optionally, when the first value attribute value of the target object is input into the early warning value attribute value prediction model, matching a corresponding early warning value attribute value interval based on the first value attribute value, and calculating the early warning value attribute value of the target object by using a first preset threshold corresponding to the early warning value attribute value interval.
Optionally, the early warning information includes early warning mail, early warning short message and forced invalidation information of value attribute information.
In another embodiment of the present invention, there is provided an apparatus for information generation, the apparatus including:
The first acquisition module is used for acquiring a first value attribute value of the target object;
The second acquisition module is used for acquiring value attribute information meeting preset conditions, wherein the preset conditions are that a first time range carried by the value attribute information contains a time point representing the current time;
A first generation module, configured to input the first value attribute value and the value attribute information into a pre-trained actual value attribute value prediction model that matches the first value attribute value of the target item, and generate an actual value attribute value of the target item, where the actual value attribute value prediction model is used to characterize a change relationship of the first value attribute value of the target item after a condition that the actual value attribute value is applied;
The second generation module is used for inputting the first value attribute value and the value attribute information into a pre-trained early warning value attribute value prediction model matched with the first value attribute value of the target object to generate an early warning value attribute value corresponding to the target object, wherein the early warning value attribute value prediction model is used for representing the corresponding relation between the first value attribute value and the early warning value attribute value of the target object;
And the third generation module is used for comparing the actual value attribute value with the early warning value attribute value and generating early warning information when the actual value attribute value is lower than the early warning value attribute value.
Optionally, the first generating module is configured to:
In the actual value attribute prediction model, the value attribute information is applied to the first value attribute value of the target item, and the actual value attribute value of the target item is calculated based on the value attribute information.
Optionally, the second generating module is configured to:
When the first value attribute value of the target object is input into the early warning value attribute value prediction model, matching a corresponding early warning value attribute value interval based on the first value attribute value, and calculating the early warning value attribute value of the target object by utilizing a first preset threshold value corresponding to the early warning value attribute value interval.
Optionally, the step of generating the early warning information includes:
the early warning information comprises early warning mail, early warning short messages and forced invalidation information of value attribute information.
In another embodiment of the present invention, a non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the steps of a method of information generation described above is provided.
In another embodiment of the present invention, there is provided a terminal device including a processor for performing each step of the above-described method for generating information.
Based on the above embodiment, firstly, a first value attribute value of a target object is obtained, secondly, value attribute information meeting a preset condition is obtained, wherein the preset condition is that a first time range carried by the value attribute information contains a time point representing the current time, further, the first value attribute value and the value attribute information are input into a pre-trained actual value attribute value prediction model matched with the first value attribute value of the target object, an actual value attribute value of the target object is generated, the actual value attribute value prediction model is used for representing the change relation of the first value attribute value of the target object after the condition of the actual value attribute value is applied, then the first value attribute value and the value attribute information are input into a pre-trained early-warning value attribute value prediction model matched with the first value attribute value of the target object, an early-warning value attribute value corresponding to the target object is generated, the pre-warning value attribute value prediction model is used for representing the corresponding relation between the first value attribute value and the value attribute value of the target object, and finally, the actual value attribute value is compared with the early-warning value attribute value, and when the actual value attribute value is lower than the early-warning value attribute value. According to the embodiment of the application, the actual value attribute value and the early warning value attribute value of the target object are set, when no association relation exists between the source data systems, the early warning mechanism is set, and when the actual value attribute value corresponding to the target object is abnormal due to the intersection of the data of each source data system, the target object with the abnormal actual value attribute value is identified and prompted, so that the efficiency and the accuracy of abnormality identification are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for generating information according to an embodiment 100 of the present application;
FIG. 2 is a schematic diagram showing a specific flow of a method for generating information according to an embodiment 200 of the present application;
FIG. 3 is a schematic diagram of system interactions in which information provided by an embodiment 300 of the present application is generated;
FIG. 4 is a diagram showing a specific flow of early warning information generation at the time of coupon abnormality according to an embodiment 400 of the present application
FIG. 5 is a diagram showing a specific flow of early warning information generation at abnormal promotion events provided for embodiment 500 of the present application
FIG. 6 shows a schematic diagram of an apparatus for information generation according to an embodiment 600 of the present application;
fig. 7 shows a schematic diagram of a terminal device according to an embodiment 700 of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be capable of being practiced otherwise than as specifically illustrated and described. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Based on the problems in the prior art, the embodiment of the application provides an information generation method, which is mainly applicable to the technical field of electronic commerce. The method for generating information is realized by identifying whether the actual value attribute of the current target object meets the early warning value attribute value or not through an actual value attribute value prediction model and an early warning value attribute value prediction model trained based on the first value attribute and the value attribute information of the target object and generating early warning information when the current actual value attribute of the target object is abnormal. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Fig. 1 is a schematic flow chart of a method for generating information according to an embodiment 100 of the present application. Wherein, the detailed steps are as follows:
S11, acquiring a first value attribute value of the target object.
In this step, the target object is mainly a commodity, which may be a commodity to be sold on an electronic commerce platform. When a user browses and selects a commodity as a target object, the first value attribute value of the target object is acquired at the same time. Wherein the first price attribute value is typically a commodity price of the commodity.
S12, acquiring value attribute information meeting preset conditions, wherein the preset conditions are that a first time range carried by the value attribute information contains a time point representing the current time.
In this step, the value attribute information in the embodiment of the present application is mainly sales promotion type information such as coupons or sales promotion for commodity prices. The e-commerce platform may be provided with a variety of different promotional type information, may be specific to a particular commodity or all commodities, etc. After the first value attribute value of the target object is obtained, the system automatically matches the value attribute information adapted to the target object based on the target object, and screens the value attribute information meeting the preset condition. Wherein the promotion type information will typically carry a first time frame representing an effective time frame. When the time point of the current time of the target object selected by the user is within the first time range, the value attribute information can be confirmed to be available, and the system acquires the value attribute information. Further, the obtained value attribute information satisfying the preset condition may be a plurality of pieces.
S13, inputting the first value attribute value and the value attribute information into a pre-trained actual value attribute value prediction model matched with the first value attribute value of the target object, and generating the actual value attribute value of the target object.
In this step, the actual value attribute value prediction model may be trained in advance based on the first value attribute value and the value attribute information of the target item. The actual value attribute value prediction model is used for representing the change relation of the first value attribute value of the target object after the condition of the actual value attribute value is applied. Specifically, the actual value attribute value prediction model is mainly applicable to the value attribute information which can be matched and used and is obtained for the first value attribute value of the target object, so as to calculate the actual value attribute value of the target object after the value attribute information is used.
S14, inputting the first value attribute value and the value attribute information into a pre-trained pre-warning value attribute value prediction model matched with the first value attribute value of the target object, and generating a pre-warning value attribute value corresponding to the target object.
In this step, the early warning value attribute value prediction model may be trained in advance based on the first value attribute value and the value attribute information of the target article. The early warning value attribute value prediction model is used for representing the corresponding relation between the first value attribute value and the early warning value attribute value of the target object. Specifically, a plurality of prediction conditions can be set in the early warning value attribute value prediction model, and further, the first value attribute value and the value attribute information of the target object are matched and calculated, and the early warning value attribute value corresponding to the target object is calculated. And calculating the early warning value attribute value of the target object based on a first preset threshold value in a plurality of value attribute value intervals set in the early warning value attribute value prediction model.
In addition, the execution sequence of step S13 and step S14 has no front-rear division, and may be executed simultaneously or sequentially.
S15, comparing the actual value attribute value with the early warning value attribute value, and generating early warning information when the actual value attribute value is lower than the early warning value attribute value.
In the step, the predicted values obtained by the target object based on the two predicted models are compared, when the actual value attribute value of the target object is lower than the early warning value attribute value, the actual value attribute value of the target object, to which the corresponding value attribute information is applicable, is considered to be abnormal, early warning information is generated at the moment, and the early warning information is displayed to a user.
As described above, based on the above embodiment, first value attribute values of the target item are obtained, next value attribute information satisfying a preset condition is obtained, wherein the preset condition is that a first time range included in the value attribute information includes a current time, further, the first value attribute values and the value attribute information are input into an actual value attribute value prediction model trained in advance and matched with the first value attribute values of the target item, an actual value attribute value of the target item is generated, wherein the actual value attribute value prediction model is used for characterizing a change relation of the first value attribute values of the target item after the condition that the actual value attribute values are applied, then the first value attribute values and the value attribute information are input into an early warning value attribute value prediction model trained in advance and matched with the first value attribute values of the target item, an early warning value attribute value corresponding to the target item is generated, wherein the early warning value attribute value prediction model is used for characterizing a correspondence relation between the first value attribute values and the early warning value attribute values of the target item, finally the actual value attribute values are compared with the early warning value attribute values, and when the actual value attribute values are lower than the early warning value attribute values. According to the embodiment of the application, the actual value attribute value and the early warning value attribute value of the target object are set, when no association relation exists between the source data systems, the early warning mechanism is set, and when the actual value attribute value corresponding to the target object is abnormal due to the intersection of the data of each source data system, the target object with the abnormal actual value attribute value is identified and prompted, so that the efficiency and the accuracy of abnormality identification are improved.
Fig. 2 is a schematic diagram of a specific flow of a method for generating information according to an embodiment 200 of the present application. The detailed process of the specific flow is as follows:
S201, acquiring a first value attribute value of the target object.
Here, in the field of electronic commerce, when a user performs an operation on a selected target item, such as adding the target item to a shopping cart, a first value attribute value of the target item is acquired. The first price attribute value is the price currently displayed by the target item.
S202, value attribute information meeting preset conditions is obtained.
Here, the value attribute information satisfying the preset condition is acquired in the set promotional information type system. For example, for the current time of 13:10:37 days of 27 months in the year 2020, browsing the purchasing target article A, wherein the first value attribute value is 200 yuan, acquiring value attribute information containing the current time in a first time range in a promotion information type system, for example, acquiring a coupon A (full 200 minus 180) with the first time range of time effect of 2020 from 15 days in the year 2020 to 30 days in the year 2020 to 24:00 in the month of end time 2020, and a promotion activity A (full two-piece octal) with the first time range of time effect of 2020 from 20 days in the month of 4 to 00:00 in the month of end time 2020 to 24:00 in the month of 4. The preset condition is mainly whether the first time range carried by the value attribute information contains the current time of the target object shopping possibly needing settlement.
S203, inputting the first value attribute value and the value attribute information into a pre-trained actual value attribute value prediction model matched with the first value attribute value of the target object, and generating an actual value attribute value of the target object.
Here, in the actual value attribute prediction model, value attribute information is applied to the first value attribute value of the target item, and the actual value attribute value of the target item is calculated based on the value attribute information. Taking coupon a in the value attribute information in step S202 as an example, the actual value attribute value of the target item is 20 after the application of the actual value attribute prediction model.
S204, an early warning value attribute value interval in the early warning value attribute value prediction model is set.
Here, the early warning system may set an early warning value attribute value interval based on the first value attribute value of the target item. Generally, the set early warning value attribute interval can be set according to the distribution condition of the first value attribute values of the electronic commerce platform and the target object, for example, the early warning value attribute interval is set to be A (1000-100000), B (500-1000), C (200-500), D (0-200) and the like.
S205, setting a first preset threshold value representing a corresponding early warning value attribute value based on the early warning value attribute value interval.
Here, the first preset threshold generally refers to a first preset threshold corresponding to the early warning value attribute value interval when the first value attribute value corresponding to the target article is within the early warning value attribute value interval in the applicable early warning value attribute value prediction model. If the first preset threshold value of the early warning value attribute value interval B (500-1000) after the coupon A is applied is set to be 0, the target commodity with the first value attribute value falling in the early warning value attribute interval can be directly applied to the value attribute information; or setting the first preset threshold value of the pre-warning value attribute value interval C (200-500) after the coupon a is applied to be 50, wherein the first value attribute value of the target commodity with the first value attribute value falling in the pre-warning value attribute interval needs to meet the condition that 200-180+30=50, namely the first value attribute value of the target commodity in the pre-warning value attribute value interval C (200-500) needs to meet 230. Further, if there are multiple target commodities in the foregoing example, it is required to consider whether the combined amount of different target commodities is less than 230, and also whether the combined amount of the same target commodity in different commodity amounts is less than 230.
S206, inputting the first value attribute value and the value attribute information into a pre-trained pre-warning value attribute value prediction model matched with the first value attribute value of the target object, and generating a pre-warning value attribute value corresponding to the target object.
Here, when the first value attribute value of the target article is input into the early warning value attribute value prediction model, the corresponding early warning value attribute value interval is matched based on the first value attribute value, and the early warning value attribute value of the target article is calculated by using a first preset threshold value corresponding to the early warning value attribute value interval. Specifically, the first preset threshold value of the pre-warning value attribute value interval C (200-500) after the coupon a is applied is set to be 50, and at this time, the first value attribute value of the target commodity with the first value attribute value falling within the pre-warning value attribute interval needs to satisfy 200-180+30=50, that is, the first value attribute value of the target commodity within the pre-warning value attribute value interval C (200-500) needs to satisfy the condition of the pre-warning value attribute value 230. Further, if there are multiple target commodities in the foregoing example, it is required to consider whether the combined amount of different target commodities is less than 230, and also whether the combined amount of the same target commodity in different commodity amounts is less than 230.
S207, comparing the actual value attribute value with the early warning value attribute value.
And S208, generating early warning information when the actual value attribute value is lower than the early warning value attribute value.
Here, when the actual value attribute value of the target object is lower than the early warning value attribute value, the early warning system generates early warning information. The early warning information comprises early warning mail, early warning short messages and forced invalidation information of value attribute information. And when the current flow is larger than the current flow, ending the current flow.
The application realizes a method for generating information based on the steps. And the actual value attribute value prediction model and the early warning value attribute value prediction model are used for early warning whether the value attribute information of the target article is applicable or not, and the early warning system is used for issuing early warning information when the sales promotion type information system containing various types of sales promotion type information is applicable to the abnormal target article. Specifically, as shown in fig. 3, a schematic diagram of system interaction where information provided in an embodiment 300 of the present application is generated is shown. The sales promotion type information system and the commodity system are relatively independent, the mutual influence generated by the sales promotion information among the systems can not be known in real time, the related target commodities are numerous, the superposition condition of the sales promotion type information is complex, and the risk can not be identified manually. The commodity system and the promotion type information system are combined to acquire the change of the value attribute information in real time, and the result is analyzed; meanwhile, parameters in the early warning value attribute value prediction model can be set according to dimensions such as the class of the target item, the first value attribute value of the target item and the like, and the effective time range of the value attribute information, promotion type information (promotion activities, coupons and the like), a first preset threshold value and early warning information (early warning mail, early warning short messages, forced invalidation and the like) can be set.
For example, when the promotion type information is a coupon, if the coupon amount is set abnormal, a failure is triggered. As shown in fig. 4, a schematic diagram of a specific flow of generating early warning information when a coupon provided by the embodiment 400 of the present application is abnormal is shown in the following specific procedure:
Store a sets a coupon a, minus 200 by 180; the effective time is 5 months and 10 days in 2020-5 months and 15 days in 2020, and no classification information of the target object and the target object is set; store A sets an early warning value attribute value interval A (1000-100000), B (500-1000), C (200-500) and D (0-200) in an early warning value attribute value prediction model according to store A and a first value attribute value (set arbitrarily according to the distribution condition of target objects); setting various parameters corresponding to the early warning attribute value interval A, B, C, D in the early warning value attribute value prediction model according to the early warning attribute value interval A, B, C, D, such as the starting time (10 days of 5 months and 10 days of 2020: 00) of value attribute information, the policy ending time (24: 00 of 15 days of 2020), promotion type information (coupons), amount type (fixed), a first preset threshold (30) and early warning information (forced failure); the promotion type information system acquires available coupon information according to a time range; acquiring first valence attribute information of a target object according to the target object used by the coupon; inputting an actual value attribute value prediction model, recalculating the actual value attribute value of the target commodity according to a first value attribute value (30), and comparing the actual value attribute value with an early warning value attribute value 210 (30+180) generated by the early warning value attribute value prediction model; when the actual value attribute value is smaller than the early warning value attribute value 210, sending early warning information, automatically disabling the coupon, or immediately correcting the coupon by a user, increasing the commodity dimension, or adjusting the coupon amount to be full 2000 minus 180; if a plurality of target objects exist, whether the sum of the combined products is smaller than 210 or not needs to be considered, and meanwhile, the combination of the different product numbers of the same target object needs to be considered; in addition, aiming at superposition of various coupons, the targeted article is used in the same way, and the mixed amount is paid to the early warning condition to start early warning.
When the promotion type information is a promotion, if the promotion is abnormal, the failure is triggered. As shown in fig. 5, a schematic diagram of a specific flow of generating early warning information when a promotional campaign is abnormal according to an embodiment 500 of the present application is shown in the following description:
Store A sets the first price attribute value of the target article A as 1000, and the sales promotion is carried out by taking full 2 items for 0.08, and the effective time of the sales promotion is from 5 months 10 days in 2020 to 5 months 15 days in 2020; store A sets an early warning attribute value interval A (1000-100000), B (500-1000), C (200-500) and D (0-200) in an early warning value attribute value prediction model according to store A and value attribute information (sales promotion activity) (optionally set according to the distribution situation of target articles); corresponding parameters in the early warning value attribute value prediction model, such as a first preset threshold value, promotion type information (promotion activity), amount type (proportion) corresponding to each early warning value interval, a first preset threshold value (30%), and early warning type (forced failure) are set according to the early warning value interval A, B, C, D; respectively inputting the target object A into an actual value attribute value prediction model and an early warning value attribute value prediction model, and calculating the actual value attribute value of A to be 160, wherein the early warning value attribute value is 2000 x 0.3=600; the actual value attribute value of the target article is smaller than the early warning value attribute value, the current sales promotion is automatically disabled, early warning information is sent at the same time, and the user immediately corrects the sales promotion, fills up 2 pieces of the sales promotion and takes 8 pieces of the sales promotion.
According to the embodiment of the application, different pre-warning value attribute value prediction models can be configured according to multiple dimensions of commodities, promotion type information, commodity classification, merchants and the like, the actual value attribute value of the value attribute information after the value attribute information is effective can be calculated in advance, the value can be adjusted at any time according to the first value attribute value and promotion type information, the pre-warning value attribute value is calculated in real time, and pre-warning information is generated aiming at abnormal promotion type information.
Based on the same inventive concept, an embodiment 600 of the present application further provides an apparatus for generating information, where, as shown in fig. 6, the apparatus includes:
a first obtaining module 61, configured to obtain a first value attribute value of a target object;
A second obtaining module 62, configured to obtain value attribute information that meets a preset condition, where the preset condition is a time point that is included in a first time range and that is carried by the value attribute information and represents a current time;
A first generation module 63, configured to input the first value attribute value and the value attribute information into a pre-trained actual value attribute value prediction model that matches the first value attribute value of the target object, and generate an actual value attribute value of the target object, where the actual value attribute value prediction model is used to characterize a change relationship of the first value attribute value of the target object after a condition that the actual value attribute value is applied;
A second generation module 64, configured to input the first value attribute value and the value attribute information into a pre-trained early-warning value attribute value prediction model that matches the first value attribute value of the target object, and generate an early-warning value attribute value corresponding to the target object, where the early-warning value attribute value prediction model is used to characterize a correspondence between the first value attribute value and the early-warning value attribute value of the target object;
the third generation module 65 is configured to compare the actual value attribute value with the early warning value attribute value, and generate early warning information when the actual value attribute value is lower than the early warning value attribute value.
In this embodiment, the specific functions and interaction manners of the first obtaining module 61, the second obtaining module 62, the first generating module 63, the second generating module 64 and the third generating module 65 can be referred to the description of the corresponding embodiment in fig. 1, and will not be repeated here.
Optionally, the first generating module 63 is configured to:
in the actual value attribute prediction model, value attribute information is applied to a first value attribute value of the target item, and an actual value attribute value of the target item is calculated based on the value attribute information.
Optionally, the second generating module 64 is configured to:
When the first value attribute value of the target object is input into the early warning value attribute value prediction model, the corresponding early warning value attribute value interval is matched based on the first value attribute value, and the early warning value attribute value of the target object is calculated by using a first preset threshold value corresponding to the early warning value attribute value interval.
Optionally, the third generating module 65 includes:
the early warning information comprises early warning mail, early warning short messages and forced invalidation information of value attribute information.
As shown in fig. 7, a further embodiment 700 of the present application further provides a terminal device, which includes a processor 701, wherein the processor 701 is configured to perform the steps of the above-mentioned method for generating information. As can also be seen from fig. 7, the terminal device provided by the above embodiment further comprises a non-transitory computer readable storage medium 702, the non-transitory computer readable storage medium 702 having stored thereon a computer program which, when executed by the processor 701, performs the steps of a method of information generation as described above. In practice, the terminal device may be one or more computers, as long as the computer readable medium and the processor are included.
In particular, the storage medium can be a general-purpose storage medium, such as a removable disk, a hard disk, a FLASH, etc., and the computer program on the storage medium, when executed, can perform each step in a method for generating information as described above. In practice, the computer readable medium may be contained in the apparatus/device/system described in the above embodiments or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs that, when executed, are capable of performing the steps of one of the information generation methods described above.
According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: portable computer diskette, hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing, but are not intended to limit the scope of the application. In the disclosed embodiments, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be combined in various combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the present application. In particular, the features recited in the various embodiments of the application and/or in the claims may be combined in various combinations and/or combinations without departing from the spirit and teachings of the application, all of which are within the scope of the disclosure.
Finally, it should be noted that: the above examples are only specific embodiments of the present application, and are not intended to limit the scope of the present application, but it should be understood by those skilled in the art that the present application is not limited thereto, and that the present application is described in detail with reference to the foregoing examples: any person skilled in the art may, within the scope of the disclosure of the present application, still make modifications to the technical solutions described in the foregoing embodiments or easily conceive of changes, or make equivalent substitutions of some of the technical features thereof; such changes, variations or substitutions, however, are not intended to depart from the spirit and scope of the embodiments of the application, and are intended to be included within the scope of the application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (8)
1. A method of information generation, comprising:
acquiring a first value attribute value of a target object;
Acquiring value attribute information meeting preset conditions, wherein the preset conditions are that a first time range carried by the value attribute information contains a time point representing the current time;
Inputting the first value attribute value and the value attribute information into a pre-trained actual value attribute value prediction model matched with the first value attribute value of the target object to generate an actual value attribute value of the target object, wherein the actual value attribute value prediction model is used for representing the change relation of the first value attribute value of the target object after the condition of applying the actual value attribute value;
Inputting the first value attribute value and the value attribute information into a pre-trained early warning value attribute value prediction model matched with the first value attribute value of the target object to generate an early warning value attribute value corresponding to the target object, wherein the early warning value attribute value prediction model is used for representing the corresponding relation between the first value attribute value and the early warning value attribute value of the target object;
Comparing the actual value attribute value with the early warning value attribute value, and generating early warning information when the actual value attribute value is lower than the early warning value attribute value;
The step of generating the early warning value attribute value corresponding to the target object comprises the following steps:
When the first value attribute value of the target object is input into the early warning value attribute value prediction model, matching a corresponding early warning value attribute value interval based on the first value attribute value, and calculating the early warning value attribute value of the target object by utilizing a first preset threshold value corresponding to the early warning value attribute value interval.
2. The method of claim 1, wherein the step of generating the actual value attribute value for the target item comprises:
in the actual value attribute value prediction model, the value attribute information is applied to the first value attribute value of the target item, and the actual value attribute value of the target item is calculated based on the value attribute information.
3. The method of claim 1, wherein the step of generating the pre-warning information comprises:
the early warning information comprises early warning mail, early warning short messages and forced invalidation information of value attribute information.
4. An apparatus for information generation, the apparatus comprising:
The first acquisition module is used for acquiring a first value attribute value of the target object;
The second acquisition module is used for acquiring value attribute information meeting preset conditions, wherein the preset conditions are that a first time range carried by the value attribute information contains a time point representing the current time;
A first generation module, configured to input the first value attribute value and the value attribute information into a pre-trained actual value attribute value prediction model that matches the first value attribute value of the target item, and generate an actual value attribute value of the target item, where the actual value attribute value prediction model is used to characterize a change relationship of the first value attribute value of the target item after a condition that the actual value attribute value is applied;
The second generation module is used for inputting the first value attribute value and the value attribute information into a pre-trained early warning value attribute value prediction model matched with the first value attribute value of the target object to generate an early warning value attribute value corresponding to the target object, wherein the early warning value attribute value prediction model is used for representing the corresponding relation between the first value attribute value and the early warning value attribute value of the target object;
the third generation module is used for comparing the actual value attribute value with the early warning value attribute value and generating early warning information when the actual value attribute value is lower than the early warning value attribute value;
wherein the second generating module is configured to:
When the first value attribute value of the target object is input into the early warning value attribute value prediction model, matching a corresponding early warning value attribute value interval based on the first value attribute value, and calculating the early warning value attribute value of the target object by utilizing a first preset threshold value corresponding to the early warning value attribute value interval.
5. The apparatus of claim 4, wherein the first generation module is configured to:
in the actual value attribute value prediction model, the value attribute information is applied to the first value attribute value of the target item, and the actual value attribute value of the target item is calculated based on the value attribute information.
6. The apparatus of claim 4, wherein the third generation module comprises:
the early warning information comprises early warning mail, early warning short messages and forced invalidation information of value attribute information.
7. A non-transitory computer readable storage medium storing instructions which, when executed by a processor, cause the processor to perform the steps of a method of information generation according to any of claims 1 to 3.
8. A terminal device comprising a processor for performing the steps of a method of information generation according to any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010560519.0A CN113762996B (en) | 2020-06-18 | 2020-06-18 | Information generation method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010560519.0A CN113762996B (en) | 2020-06-18 | 2020-06-18 | Information generation method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113762996A CN113762996A (en) | 2021-12-07 |
| CN113762996B true CN113762996B (en) | 2024-04-16 |
Family
ID=78785480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010560519.0A Active CN113762996B (en) | 2020-06-18 | 2020-06-18 | Information generation method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113762996B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109785072A (en) * | 2019-01-23 | 2019-05-21 | 北京京东尚科信息技术有限公司 | Method and apparatus for generating information |
| CN110348688A (en) * | 2019-06-12 | 2019-10-18 | 江苏富山软件科技有限公司 | A kind of property tax prewarning management method and its system |
| CN110852772A (en) * | 2018-08-21 | 2020-02-28 | 北京京东尚科信息技术有限公司 | Dynamic pricing method, system, device and storage medium |
| CN110880119A (en) * | 2018-09-05 | 2020-03-13 | 北京京东尚科信息技术有限公司 | Data processing method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110040656A1 (en) * | 2009-08-12 | 2011-02-17 | Groetzinger Jon D | System and method for generating predictions of price and availability of event tickets on secondary markets |
| US20130218736A1 (en) * | 2012-02-22 | 2013-08-22 | Markit North America, Inc. | Crossed market alert method for over-the-counter (otc) markets |
| US20180150869A1 (en) * | 2013-07-19 | 2018-05-31 | Jet.com, Inc. | System, method, and program product for identifying discounted items |
-
2020
- 2020-06-18 CN CN202010560519.0A patent/CN113762996B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852772A (en) * | 2018-08-21 | 2020-02-28 | 北京京东尚科信息技术有限公司 | Dynamic pricing method, system, device and storage medium |
| CN110880119A (en) * | 2018-09-05 | 2020-03-13 | 北京京东尚科信息技术有限公司 | Data processing method and device |
| CN109785072A (en) * | 2019-01-23 | 2019-05-21 | 北京京东尚科信息技术有限公司 | Method and apparatus for generating information |
| CN110348688A (en) * | 2019-06-12 | 2019-10-18 | 江苏富山软件科技有限公司 | A kind of property tax prewarning management method and its system |
Non-Patent Citations (2)
| Title |
|---|
| Reference effect and inventory constraint on optimal pricing for daily perishable products;Takeshi Koide;《2009 IEEE International Conference on Industrial Engineering and Engineering Management》;全文 * |
| 不同促销模式下零售商需求预测精确性的影响研究;许明辉;《管理学报》;第14卷(第9期);1384-1393 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113762996A (en) | 2021-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6275923B2 (en) | Measure evaluation system and measure evaluation method | |
| US20210224868A1 (en) | Product valuation system and method | |
| CN110197408B (en) | Pricing early warning method and system for premium commodities | |
| Valpeters et al. | Application of machine learning methods in big data analytics at management of contracts in the construction industry | |
| US11842293B2 (en) | Systems and methods for short identifier behavioral analytics | |
| Terminanto et al. | Implementation of enterprise resource planning using Odoo module sales and CRM. Case study: PT Ecosains Hayati | |
| US20160034928A1 (en) | Systems and methods for promotional forecasting | |
| Lestari et al. | Risk mitigation via integrating house of risk and probability impact matrix in halal food supply chain | |
| US10497018B1 (en) | Method and system to account for price variation in attribution models in advertising | |
| Freitag et al. | A concept for a consumer-centered sustainable last mile logistics | |
| US20220188756A1 (en) | Systems and methods for inventory control and optimization | |
| CN113762996B (en) | Information generation method, device and storage medium | |
| JP6067630B2 (en) | Profit / loss prediction apparatus and profit / loss prediction program | |
| US20180165715A1 (en) | System and Method for Measuring Customer Behavior | |
| JP2016133816A (en) | Commodity demand prediction system | |
| US20170178164A1 (en) | Systems and Methods for Use in Processing Transaction Data | |
| JP2020042863A (en) | Information processor, information processor control method and program | |
| CN112017000B (en) | Commodity information pushing method, device, equipment and storage medium | |
| CN109360019A (en) | A kind of personal vehicles price evaluation method | |
| US10607174B2 (en) | Proactive simulation and detection of outbreaks based on product data | |
| US20200242644A1 (en) | System and method using a dynamic pricing engine to determine pricing for goods | |
| US20170228751A1 (en) | Systems and methods for dynamic value calculation and update across distributed servers | |
| CN110084541B (en) | Method and apparatus for predicting supplier delivery duration | |
| Babiloni et al. | Stock control analytics: a data-driven approach to compute the fill rate considering undershoots | |
| CN109961313A (en) | A kind of information-pushing method and information push-delivery apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |