A commodity sales data prediction method, device and medium based on public opinion
By identifying product tags and similar products, collecting public opinion information to generate keywords, calculating the public opinion influence index, and using machine learning models for training, the problem of accuracy in predicting online product sales data has been solved, enabling effective prediction and risk management of online product sales.
Patent Information
- Application Number
- CN202210875577.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-25
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2042-07-25
AI Technical Summary
Existing technologies fail to effectively consider the impact of online public opinion on product sales, making it impossible to accurately predict online product sales data in the short term.
By identifying product tags and similar products, collecting public opinion information and generating keyword information, calculating the public opinion influence index, generating sales forecast curves, and training and adjusting machine learning models, accurate predictions of online product sales can be achieved.
It provides a reasonable early warning and monitoring platform to help enterprises cope with risks, improve marketing and sales expectations, support local governments in formulating network economy policies, and effectively assist e-commerce.
Smart Images

Figure CN115115417B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data analysis, and specifically to a method, device and medium for predicting commodity sales data based on public opinion. Background Art
[0002] With the standardization and popularization of online sales, it is not difficult to find that online product sales are closely related to online public opinion. Well-known marketing methods such as Internet celebrity marketing can often drive the sales volume of online products, while negative news can also cause a cold winter for online sales of individual products.
[0003] In the prior art, although there are analysis and prediction methods for online commodity sales data, these methods do not take into account the impact of online public opinion on commodity sales, and therefore cannot accurately predict online commodities that have public opinion in the short term. Summary of the invention
[0004] In order to solve the above problems, the present application proposes a method, device and medium for predicting commodity sales data based on public opinion, wherein the method includes: determining the commodity label of the target commodity, the commodity label at least including a category label and a brand label; determining similar commodities of the target commodity based on the commodity label; collecting public opinion information of the target commodity, and generating keyword information of the public opinion information; the keyword information at least includes keywords, keyword index and keyword part of speech; determining a first public opinion influence index of the target commodity based on the keyword information and the historical sales data of the similar commodities; generating a first sales forecast curve of the target commodity based on the first public opinion influence index and the sales data of the target commodity.
[0005] In one example, after generating the first sales forecast curve of the target product, the method further includes: collecting subsequent public opinion information and subsequent sales data of the target product at preset collection time intervals; if the keyword information of the subsequent public opinion information has not changed, training the first public opinion influence index based on the subsequent sales data and the subsequent public opinion information to obtain a second public opinion influence index; and generating a second sales forecast curve for the target product based on the second public opinion influence index and the subsequent sales data.
[0006] In one example, after collecting subsequent public opinion information of the target product at the preset collection time interval, the method also includes: if the keyword information changes, determining the third public opinion influence index of the target product based on the changed keyword information and the historical sales data of the similar products; generating a third sales forecast curve of the target product based on the third public opinion influence index and the subsequent sales data.
[0007] In one example, after generating the second sales forecast curve of the target product, the method further includes: saving the second public opinion influence index to a database; and using the second public opinion influence index as the public opinion influence index corresponding to the keyword information and the target product label.
[0008] In one example, before generating keyword information of the public opinion information, the method further includes: obtaining manually input keyword information and generating a keyword dictionary; confirming a preset initial model, and training the initial model through the keyword dictionary to obtain a keyword generation model.
[0009] In one example, after generating the keyword information of the public opinion information, the method further includes: determining a product label of the product affected by the public opinion information corresponding to the keyword information; and generating a fourth sales forecast curve of the product affected by the product based on the product label.
[0010] In one example, after generating the first sales forecast curve of the target product, the method further includes: obtaining subsequent sales data of the target product, and if the subsequent sales data differs too much from the first sales forecast curve, listing the product as an abnormal product; determining a purchasing population label for the abnormal product; determining a public opinion influence coefficient of the abnormal product based on the purchasing population label; and modifying the first sales forecast curve based on the public opinion influence coefficient to obtain a fifth sales forecast curve.
[0011] In one example, before collecting the public opinion information of the target product, the method further includes: determining the classification level of the keyword index in advance according to the scope of public opinion influence of the public opinion information.
[0012] The present application also provides a commodity sales data prediction device based on public opinion, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute: determining a commodity label of a target commodity, wherein the commodity label at least includes a category label and a brand label; determining similar commodities of the target commodity based on the commodity label; collecting public opinion information of the target commodity, and generating keyword information of the public opinion information; the keyword information at least includes keywords, keyword indexes and keyword parts of speech; determining a first public opinion influence index of the target commodity based on the keyword information and the historical sales data of the similar commodities; and generating a first sales volume prediction curve of the target commodity based on the first public opinion influence index and the sales data of the target commodity.
[0013] The present application also provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to: determine a product label of a target product, wherein the product label includes at least a category label and a brand label; determine similar products of the target product based on the product label; collect public opinion information of the target product, and generate keyword information of the public opinion information; the keyword information includes at least keywords, keyword indexes, and keyword parts of speech; determine a first public opinion influence index of the target product based on the keyword information and historical sales data of the similar products; and generate a first sales forecast curve of the target product based on the first public opinion influence index and the sales data of the target product.
[0014] The method proposed in this application can bring the following beneficial effects: a reasonable early warning monitoring platform helps enterprises deal with risks, and marketing sales expectations also help manufacturers balance product and marketing expenses. The establishment and improvement of the network sales commodity big data expectation analysis system based on natural language analysis system and artificial intelligence can help local governments to formulate and improve network economic policies, and provide corresponding data references and early warnings, which is an effective aid to the development of e-commerce. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0016] Figure 1 A flowchart of a method for predicting commodity sales data based on public opinion in an embodiment of the present application;
[0017] Figure 2 This is a schematic diagram of the structure of a commodity sales data prediction device based on public opinion in an embodiment of the present application. DETAILED DESCRIPTION
[0018] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0019] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0020] Figure 1A flowchart of a method for predicting commodity sales data based on public opinion provided for one or more embodiments of this specification. The method can be applied to different types of commodities, such as food commodities, kitchenware commodities, clothing commodities, digital electronic commodities, furniture commodities, etc. The process can be executed by a computing device in the corresponding field (such as a risk control server or smart mobile terminal corresponding to a payment service), and some input parameters or intermediate results in the process allow manual intervention and adjustment to help improve accuracy.
[0021] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.
[0022] It should be noted that the server may be a single device or a system consisting of multiple devices, that is, a distributed server, and this application does not make any specific limitation on this.
[0023] like Figure 1 As shown, the embodiment of the present application provides a commodity sales data prediction method based on public opinion, including:
[0024] S101: Determine a product label of a target product, where the product label at least includes a category label and a brand label.
[0025] First, you need to determine the product label of the target product. The target product here is the product waiting for sales data prediction. The product label refers to the product attributes of the product, such as product type and product brand.
[0026] S102: Determine similar products of the target product according to the product tag.
[0027] In order to predict the sales data of the target product, it is necessary to determine similar products of the target product. When determining similar products of the target product, the product labels can be used for determination. For example, if the target product is a food product, similar products can be selected from products containing food product labels.
[0028] It should be noted that the historical sales data of the target product and similar products are known, and the historical sales data can be pre-stored in a storage device of a computer device. When a prediction of the target product is required, the computer device can select the historical sales data from the storage device. Of course, the computer device can also obtain the historical sales data from other external devices. For example, the historical sales data is stored in the cloud, and when a prediction of the target product is required, the computer device can obtain the historical sales data from the cloud. This embodiment does not limit the method for obtaining the historical sales data.
[0029] S103: Collect public opinion information of the target product and generate keyword information of the public opinion information; the keyword information at least includes keywords, keyword index and keyword part of speech.
[0030] In order to analyze and estimate the impact of online public opinion on commodity sales, it is necessary to collect public opinion information related to the target commodity. The public opinion information here refers to the information related to the target commodity circulated on the Internet. Then generate keyword information of the target commodity and the public opinion information based on the public opinion information. The keyword information here includes at least keywords, keyword indexes, and keyword parts of speech. The keyword index here refers to the degree of fermentation of public opinion events, and the part of speech refers to whether the keyword is positive, negative, or neutral. In an example, the keywords can be set as follows: Keywords: Internet celebrity; Part of speech: short-term growth index, positive; Category: pre-prepared dishes, such as milk tea. Keywords: sauerkraut; Part of speech: long-term negative index, negative; Category: pre-prepared dishes, pickled products, convenience foods. Keywords: Qinghai-Tibet; Part of speech: long-term growth index, neutral; Category: none.
[0031] S104: Determine a first public opinion influence index of the target product according to the keyword information and the historical sales data of the similar products.
[0032] After obtaining the keywords corresponding to the current public opinion situation and the target product, the first public opinion impact index of the target product can be determined based on the keyword information and the historical sales data of similar products. The first public opinion impact index here refers to the impact index of the current public opinion situation on the sales volume of the target product. It should be noted that the first public opinion impact index here is obtained by comparing the changes in the historical sales curve of similar products with the data of the same period when similar products did not have the same public opinion situation. For example, taking negative keywords as an example, if a food product has negative public opinion on the Internet, similar products to the food product should be found, and it is required that the same public opinion heat and negative public opinion appear in the sales history of similar products. By comparing the sales data of the similar product with the sales data of the same period when no negative public opinion occurred, the impact of negative public opinion on the sales of similar products can be obtained, which can be used as the sales impact of the target product.
[0033] S105: Generate a first sales volume prediction curve of the target product according to the first public opinion influence index and the sales data of the target product.
[0034] After knowing the first public opinion influence index, the first sales forecast curve of the target product can be obtained based on the original sales data of the target product and the first public opinion influence index. If the first public opinion influence index is a 30% year-on-year decrease in quarterly sales, it can be predicted that the quarterly sales of the target product will decrease by 30%, and the sales forecast curve of the target product can be obtained.
[0035] In one embodiment, after obtaining the first sales forecast curve of the target product, since the first public opinion influence index is obtained through the historical sales data of similar products, the sales predicted by the first sales forecast curve may not be accurate enough, but the prediction accuracy and prediction range can be gradually improved by continuously collecting prediction data and actual sales data and performing comparative training, thereby achieving sustainability of the system. Specifically, it includes: collecting subsequent public opinion information and subsequent sales data of the target product at preset collection time intervals; if the keyword information of the subsequent public opinion information has not changed, that is, the public opinion has not further fermented or cooled, then according to the subsequent sales data and subsequent public opinion information, the first public opinion influence index is trained to obtain the second public opinion influence index. Then, based on the second public opinion influence index and subsequent sales data, the second sales forecast curve of the target product is generated.
[0036] Furthermore, if the keyword information changes, that is, the public opinion of the current target product further increases or has gradually cooled down, the third public opinion influence index of the target product is determined based on the changed keyword information and the historical sales data of similar products. Then, based on the third public opinion influence index and subsequent sales data, the third sales forecast curve of the target product is generated.
[0037] In one embodiment, after generating the second sales forecast curve of the target product, the second public opinion influence index is saved in the database, and the second public opinion influence index is used as the public opinion influence index corresponding to the keyword information and the target product label. When similar products of the target product need to be predicted later, the second public opinion influence index can be used as the first public opinion influence index of the similar products.
[0038] In one embodiment, when keywords of public opinion information are generated, it is done through a keyword generation model. Therefore, before generating keywords, it is necessary to manually input a part of the keyword information to form a keyword dictionary, and then confirm the preset initial model, and train the initial model through the keyword dictionary to obtain a keyword generation model. After the public opinion information is subsequently collected, the public opinion information can be directly input into the keyword generation model to obtain the keywords corresponding to the public opinion information.
[0039] It should be noted that the sales forecast model and keyword generation model are mathematical models constructed based on machine learning algorithms, including but not limited to neural network models, support vector machine models, etc. The constructed sales forecast model and keyword generation model are pre-trained through training data sets. When the set training precision and accuracy are reached, it is determined that the sales forecast model and keyword generation model of the current training have completed training so that they can be used for prediction processing.
[0040] In one embodiment, not only can the public opinion information related to the target product be found through the target product, but also the product that will be affected by the public opinion information can be found through the public opinion information suddenly released on the Internet. Specifically, it includes: determining the product label of the product affected by the public opinion information according to the keyword information; generating the fourth sales prediction curve of the product affected according to the product label.
[0041] In one embodiment, since the audience of some commodities is children or the elderly, even if public opinion breaks out on the Internet for such commodities, since the audience will not pay too much attention to online information, the sales volume of such commodities will not be greatly affected by public opinion like other commodities. At this time, when predicting the sales volume of such commodities, the process cannot be the same as that of ordinary commodities. Therefore, after generating the first sales volume prediction curve of the target commodity, the subsequent sales data of the target commodity is obtained. If the gap between the subsequent sales data and the first sales volume prediction curve is too large, the commodity is listed as an abnormal commodity. Determine the purchase population label of the abnormal commodity, that is, the audience population label of the abnormal commodity. Determine the public opinion influence coefficient of the abnormal commodity according to the purchase population label. It should be noted that the public opinion influence coefficient is different from the public opinion influence index in the previous text. The public opinion influence coefficient is determined based on the audience population label, and acts on the sales volume prediction of the abnormal commodity together with the public opinion influence index during prediction. Then modify the first sales volume prediction curve according to the public opinion influence coefficient to obtain the fifth sales volume prediction curve.
[0042] In one embodiment, before collecting public opinion information of a target product, it is also necessary to determine the classification level of the keyword index in advance according to the scope of public opinion influence of the public opinion information.
[0043] like Figure 2 As shown, the embodiment of the present application also provides a commodity sales data prediction method based on public opinion, including:
[0044] at least one processor; and,
[0045] a memory communicatively connected to the at least one processor; wherein,
[0046] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:
[0047] Determine a product label of a target product, wherein the product label includes at least a category label and a brand label; determine similar products of the target product based on the product label; collect public opinion information of the target product, and generate keyword information of the public opinion information; the keyword information includes at least keywords, keyword indexes, and keyword parts of speech; determine a first public opinion influence index of the target product based on the keyword information and historical sales data of the similar products; and generate a first sales forecast curve of the target product based on the first public opinion influence index and the sales data of the target product.
[0048] The embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as follows:
[0049] Determine a product label of a target product, wherein the product label includes at least a category label and a brand label; determine similar products of the target product based on the product label; collect public opinion information of the target product, and generate keyword information of the public opinion information; the keyword information includes at least keywords, keyword indexes, and keyword parts of speech; determine a first public opinion influence index of the target product based on the keyword information and historical sales data of the similar products; and generate a first sales forecast curve of the target product based on the first public opinion influence index and the sales data of the target product.
[0050] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0051] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.
[0052] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0053] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0054] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0055] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0056] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0057] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0058] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0059] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0060] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A commodity sales data prediction method based on public opinion, characterized in that: include: Determine a product label of the target product, wherein the product label includes at least a category label and a brand label; Determining similar products of the target product according to the product label; Collecting public opinion information of the target product and generating keyword information of the public opinion information; the keyword information at least includes keywords, keyword index and keyword part of speech; Determining a first public opinion influence index of the target product according to the keyword information and the historical sales data of the similar products; generating a first sales volume prediction curve of the target product according to the first public opinion influence index and the sales data of the target product; After generating the keyword information of the public opinion information, the method further includes: Determine, based on the keyword information, a product label that affects the product and corresponds to the public opinion information; generating a fourth sales volume prediction curve of the influencing product according to the product label; After generating the first sales forecast curve of the target product, the method further includes: Obtaining subsequent sales data of the target product, and if the subsequent sales data differs too much from the first sales volume forecast curve, listing the product as an abnormal product; Determine the purchaser labels of the abnormal products; Determining the public opinion influence coefficient of the abnormal product according to the purchasing group label; The fourth sales forecast curve is modified according to the public opinion influence coefficient to obtain a fifth sales forecast curve.
2. The method according to claim 1, characterized in that: After generating the first sales forecast curve of the target product, the method further includes: At preset collection time intervals, collect subsequent public opinion information and subsequent sales data of the target product; If the keyword information of the subsequent public opinion information has not changed, training the first public opinion influence index according to the subsequent sales data and the subsequent public opinion information to obtain a second public opinion influence index; A second sales volume forecast curve for the target product is generated according to the second public opinion influence index and the subsequent sales data.
3. The method according to claim 2, characterized in that After collecting subsequent public opinion information of the target product at the preset collection time interval, the method further includes: If the keyword information changes, the third public opinion influence index of the target product is determined according to the changed keyword information and the historical sales data of the similar products; A third sales volume prediction curve of the target product is generated according to the third public opinion influence index and the subsequent sales data.
4. The method according to claim 2, characterized in that: After generating the second sales forecast curve of the target product, the method further includes: Saving the second public opinion influence index to a database; The second public opinion influence index is used as the public opinion influence index corresponding to the keyword information and the target product label.
5. The method according to claim 1, characterized in that Before generating the keyword information of the public opinion information, the method further includes: Obtain manually input keyword information and generate a keyword dictionary; A preset initial model is confirmed, and the initial model is trained through the keyword dictionary to obtain a keyword generation model.
6. The method according to claim 1, characterized in that Before collecting the public opinion information of the target product, the method further includes: According to the scope of public opinion influence of the public opinion information, the classification level of the keyword index is determined in advance.
7. A commodity sales data prediction device based on public opinion, characterized in that: include: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute: Determine a product label of the target product, wherein the product label includes at least a category label and a brand label; Determining similar products of the target product according to the product label; Collecting public opinion information of the target product and generating keyword information of the public opinion information; the keyword information at least includes keywords, keyword index and keyword part of speech; Determining a first public opinion influence index of the target product according to the keyword information and the historical sales data of the similar products; generating a first sales volume prediction curve of the target product according to the first public opinion influence index and the sales data of the target product; After the keyword information of the public opinion information is generated, determining a product label that affects the product corresponding to the public opinion information according to the keyword information; generating a fourth sales volume prediction curve of the influencing product according to the product label; After generating the first sales forecast curve of the target product, obtaining subsequent sales data of the target product, and if the subsequent sales data differs too much from the first sales forecast curve, listing the product as an abnormal product; Determine the purchaser labels of the abnormal products; Determining the public opinion influence coefficient of the abnormal product according to the purchasing group label; The fourth sales forecast curve is modified according to the public opinion influence coefficient to obtain a fifth sales forecast curve.
8. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Determine a product label of the target product, wherein the product label includes at least a category label and a brand label; Determining similar products of the target product according to the product label; Collecting public opinion information of the target product and generating keyword information of the public opinion information; the keyword information at least includes keywords, keyword index and keyword part of speech; Determining a first public opinion influence index of the target product according to the keyword information and the historical sales data of the similar products; generating a first sales volume prediction curve of the target product according to the first public opinion influence index and the sales data of the target product; After the keyword information of the public opinion information is generated, determining a product label that affects the product corresponding to the public opinion information according to the keyword information; generating a fourth sales volume prediction curve of the influencing product according to the product label; After generating the first sales forecast curve of the target product, obtaining subsequent sales data of the target product, and if the subsequent sales data differs too much from the first sales forecast curve, listing the product as an abnormal product; Determine the purchaser labels of the abnormal products; Determining the public opinion influence coefficient of the abnormal product according to the purchasing group label; The fourth sales forecast curve is modified according to the public opinion influence coefficient to obtain a fifth sales forecast curve.
Citation Information
Patent Citations
Big data sales forecasting method for household appliance industry
CN109214601A
Clothing sales trend prediction method based on historical similar products
CN111815349A
Sales prediction method based on policy-public opinion-purchase double-order deep learning
CN114511345A
Network public opinion analysis method and apparatus, and computer-readable storage medium
WO2019227710A1
