Product influence degree prediction method, equipment, storage medium and device

Abstract

The invention discloses a product influence degree prediction method, equipment, a storage medium and a device, and the method comprises the steps: carrying out the multi-dimensional information statistics of buying amount user information corresponding to an upstream product chain in a product matrix resource according to a preset influence factor dimension, and obtaining the influence information of a target dimension; and performing influence degree prediction on a downstream product chain corresponding to the upstream product chain according to the influence information to obtain an influence degree prediction result. According to the invention, the multi-dimensional information statistics is carried out on the buying amount user information corresponding to the upstream product chain through the preset influence factor dimension, and the influence degree prediction is carried out on the downstream product chain according to the influence information obtained through statistics, so that compared with the prior art in which a large amount of manpower and time costs need to be input through manual statistics, the method has the advantages that the time cost is reduced; according to the method, the contribution degree of the single product in the product matrix chain to other product lines is scientifically and reasonably evaluated from a global perspective, and the influence degree of the upstream product to the downstream product is clarified.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a product impact prediction method, equipment, storage medium and device. Background Art

[0002] With the development of software technology, a company or organization will have multiple software product lines. At the same time, when there are related product matrices between software product lines, the stickiness between products can be determined by determining the influence between products, and then the data of downstream products under the product line within a period of time can be estimated. However, most of the existing solutions are based on professional managers manually analyzing the influence between upstream products and downstream products in the historical industrial line through statistical analysis, and then estimating the value that downstream products can generate within a limited time period. However, the above method cannot analyze data in real time, resulting in low data accuracy. In addition, due to the complexity of product lines, manual statistics will require a lot of manpower and time costs, and it is impossible to scientifically and reasonably evaluate the value of a single product to other product lines under the product matrix chain and clarify the influence of upstream products on downstream products.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a product impact prediction method, equipment, storage medium and device, aiming to solve the technical problem that the existing technology cannot scientifically and reasonably evaluate the value of a single product to other product lines under the product matrix chain and clarify the impact of upstream products on downstream products.

[0005] To achieve the above object, the present invention provides a product influence prediction method, which comprises the following steps:

[0006] Obtain the purchasing user information corresponding to the upstream product chain in the product matrix resources;

[0007] Perform multi-dimensional information statistics on the user information of the purchased volume according to the preset impact factor dimension to obtain the impact information of the target dimension;

[0008] An influence degree prediction is performed on the downstream product chain corresponding to the upstream product chain according to the influence information to obtain an influence degree prediction result.

[0009] Optionally, before the step of performing multi-dimensional information statistics on the buying volume user information according to the preset influence evaluation dimension to obtain the influence information of the target dimension, the step further includes:

[0010] Determine the traffic-driving user information of the upstream product chain according to the preset statistical caliber and the buying user information;

[0011] The downstream product chain corresponding to the upstream product chain is determined according to the guide belt quantity user information.

[0012] Optionally, the preset impact factor dimension includes a volume dimension and a quality dimension, and the step of performing multi-dimensional information statistics on the volume-buying user information according to the preset impact factor dimension to obtain impact information of the target dimension includes:

[0013] The buying volume user information is counted according to the volume dimension to obtain the product new user volume information corresponding to the volume dimension;

[0014] The buying volume user information is counted according to the quality dimension to obtain the number of product active days corresponding to the quality dimension;

[0015] The impact information is determined based on the information on the number of new users of the product and the number of active days of the product.

[0016] Optionally, the step of determining the influence information according to the information on the number of new users of the product and the number of active days of the product includes:

[0017] Counting the amount of new users of the product according to a preset statistical period to obtain a first statistical result;

[0018] Counting the number of active days of the product according to the preset statistical period to obtain a second statistical result;

[0019] Influence information is determined according to the first statistical result and the second statistical result.

[0020] Optionally, the step of performing an influence prediction on the downstream product chain corresponding to the upstream product chain according to the influence information to obtain an influence prediction result includes:

[0021] Determine the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the first statistical result and the second statistical result;

[0022] Based on the preset time series model and the comprehensive influence, an influence prediction is performed on the downstream product chain corresponding to the upstream product chain to obtain an influence prediction result.

[0023] Optionally, the step of determining the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the first statistical result and the second statistical result includes:

[0024] Determine the newly added user information of the downstream product chain corresponding to the volume dimension within the target period according to the preset LR model and the first statistical result;

[0025] Determine the average active days per traffic diverter corresponding to the quality dimension of the downstream product chain according to the second statistical result;

[0026] The comprehensive influence of the downstream product chain corresponding to the target period is determined according to the preset statistical logic, the newly added user information of the diversion and the average active days of the diversion users.

[0027] Optionally, the step of determining the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the newly added user information of the diversion, and the average number of active days per person of the diversion includes:

[0028] Determine the daily comprehensive impact of newly added paying users based on the preset statistical logic, the newly added user information of the diversion, and the average number of active days per person of the diversion;

[0029] Determine the monthly comprehensive impact corresponding to the monthly newly added paying users according to the preset statistical logic, the newly added user information of the diversion and the average active days of the diversion users;

[0030] The comprehensive impact of the downstream product chain is determined according to the daily comprehensive impact and the monthly comprehensive impact.

[0031] Optionally, after the step of performing an influence prediction on the downstream product chain corresponding to the upstream product chain according to the influence information and obtaining the influence prediction result, the step further includes:

[0032] Generate a traffic diversion ecological map between product matrices according to the impact prediction results;

[0033] A diversion trend graph corresponding to the volume dimension and the quality dimension is generated according to the preset time series model and the diversion ecological graph.

[0034] Optionally, after the step of performing an influence prediction on the downstream product chain corresponding to the upstream product chain according to the influence information and obtaining the influence prediction result, the step further includes:

[0035] A business impact analysis graph is generated based on the newly added user information of the diversion, the average active days of the diversion users, the comprehensive impact and the impact prediction result, and the business impact analysis graph is displayed.

[0036] Optionally, the calculation method of the daily comprehensive impact includes:

[0037] Daily new paying users = annual conversion rate * average monthly active days per person. The annual conversion rate refers to the proportion of new downstream users introduced by upstream paying users within one year.

[0038] Daily comprehensive impact = (annual new users * average monthly active days per person) / daily new paying users.

[0039] Optionally, the calculation method of the monthly comprehensive impact includes:

[0040] Determine the annual new users of the monthly new paying users according to the daily average annual conversion rate and the monthly new paying users, where annual new users = monthly new paying users * daily average annual conversion rate;

[0041] The monthly comprehensive influence is determined based on the daily average annual conversion rate and the daily average monthly active days per person, where the monthly comprehensive influence = daily average annual conversion rate * daily average monthly active days per person.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes a product influence prediction device, which includes a memory, a processor, and a product impact prediction program stored in the memory and executable on the processor, and the product impact prediction program is configured to implement the steps of product impact prediction as described above.

[0043] In addition, to achieve the above objectives, the present invention also proposes a storage medium, on which a product influence prediction program is stored, and when the product influence prediction program is executed by a processor, the steps of the product influence prediction method described above are implemented.

[0044] In addition, to achieve the above-mentioned purpose, the present invention further proposes a product influence prediction device, the product influence prediction device comprising:

[0045] The information acquisition module is used to obtain the purchasing user information corresponding to the upstream product chain in the product matrix resources;

[0046] An information determination module, used to perform multi-dimensional information statistics on the user information of the purchased volume according to preset impact factor dimensions to obtain impact information of the target dimension;

[0047] The influence prediction module is used to predict the influence of the downstream product chain corresponding to the upstream product chain according to the influence information to obtain the influence prediction result.

[0048] Optionally, the product influence prediction device further includes a product chain determination module;

[0049] The product chain determination module is used to determine the traffic volume user information of the upstream product chain according to the preset statistical caliber and the purchase volume user information;

[0050] The product chain determination module is further used to determine the downstream product chain corresponding to the upstream product chain according to the guide belt quantity user information.

[0051] Optionally, the preset influencing factor dimension includes a volume dimension and a quality dimension, and the information determination module is further used to count the volume-buying user information according to the volume dimension to obtain the product new user quantity information corresponding to the volume dimension;

[0052] The information determination module is further used to collect statistics on the user information of the purchased volume according to the quality dimension to obtain the number of active days of the product corresponding to the quality dimension;

[0053] The information determination module is further used to determine the impact information based on the information on the number of new users of the product and the number of active days of the product.

[0054] Optionally, the information determination module is further used to collect statistics on the amount of new users of the product according to a preset statistical period to obtain a first statistical result;

[0055] The information determination module is further used to count the number of active days of the product according to the preset statistical period to obtain a second statistical result;

[0056] The information determination module is further used to determine the impact information according to the first statistical result and the second statistical result.

[0057] Optionally, the influence prediction module is further used to determine the comprehensive influence of the downstream product chain corresponding to the target period according to a preset statistical logic, the first statistical result and the second statistical result;

[0058] The influence prediction module is further used to predict the influence of the downstream product chain corresponding to the upstream product chain based on a preset time series model and the comprehensive influence, so as to obtain an influence prediction result.

[0059] Optionally, the influence prediction module is further used to determine the newly added user information of the downstream product chain corresponding to the volume dimension within the target period according to the preset LR model and the first statistical result;

[0060] The influence prediction module is further used to determine the average active days per traffic diversion person corresponding to the quality dimension of the downstream product chain according to the second statistical result;

[0061] The influence prediction module is also used to determine the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the information of the newly added users of the diversion, and the average active days of the diversion users.

[0062] Optionally, the influence prediction module is further used to determine the daily comprehensive influence corresponding to the daily newly added paying users according to the preset statistical logic, the newly added user information of the diversion and the average active days of the diversion users;

[0063] The influence prediction module is further used to determine the monthly comprehensive influence corresponding to the monthly newly added paying users according to the preset statistical logic, the newly added user information of the diversion and the average active days of the diversion users;

[0064] The impact prediction module is further used to determine the comprehensive impact of the downstream product chain according to the daily comprehensive impact and the monthly comprehensive impact.

[0065] The present invention obtains the user information of the volume buyers corresponding to the upstream product chain in the product matrix resources; performs multi-dimensional information statistics on the user information of the volume buyers according to the preset influencing factor dimension to obtain the influencing information of the target dimension; performs an influence prediction on the downstream product chain corresponding to the upstream product chain according to the influencing information to obtain the influencing prediction result. Since the present invention performs multi-dimensional information statistics on the user information of the volume buyers corresponding to the upstream product chain according to the preset influencing factor dimension, and predicts the influencing degree of the downstream product chain according to the statistically obtained influencing information, compared with the prior art that requires a lot of manpower and time costs to perform statistics manually, it is impossible to scientifically and reasonably evaluate the value of a single product under the product matrix chain to other product lines, and it is impossible to clarify the influence of upstream products on downstream products. The present invention achieves scientific and reasonable evaluation of the contribution of a single product under the product matrix chain to other product lines from a global perspective while measuring the value of the single product itself, and clarifies the influence of upstream products on downstream products, so as to maximize the value under the product matrix. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a schematic diagram of the structure of a product impact prediction device for a hardware operating environment involved in an embodiment of the present invention;

[0067] Figure 2 It is a flow chart of the first embodiment of the product influence prediction method of the present invention;

[0068] Figure 3 It is a flow chart of the second embodiment of the product influence prediction method of the present invention;

[0069] Figure 4 Schematic diagram of paid user influence in the second embodiment of the product influence prediction method of the present invention

[0070] Figure 5 A schematic diagram of business impact analysis of a second embodiment of a product impact prediction method of the present invention;

[0071] Figure 6 This is a structural block diagram of the first embodiment of the product influence prediction device of the present invention.

[0072] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0073] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0074] Reference Figure 1 , Figure 1 It is a schematic diagram of the structure of a product impact prediction device for a hardware operating environment involved in an embodiment of the present invention.

[0075] like Figure 1 As shown, the product impact prediction device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), and the user interface 1003 may also include a standard wired interface and a wireless interface. The wired interface of the user interface 1003 may be a USB interface in the present invention. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable memory (Non-volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0076] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the product impact prediction device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0077] like Figure 1 As shown, the memory 1005 identified as a computer storage medium may include an operating system, a network communication module, a user interface module, and a product impact prediction program.

[0078] exist Figure 1 In the product influence prediction device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the user device; the product influence prediction device calls the product influence prediction program stored in the memory 1005 through the processor 1001, and executes the product influence prediction method provided by the embodiment of the present invention.

[0079] Based on the above hardware structure, an embodiment of the product influence prediction method of the present invention is proposed.

[0080] Reference Figure 2 , Figure 2 The figure is a flow chart of the first embodiment of the method for predicting product influence of the present invention, and proposes the first embodiment of the method for predicting product influence of the present invention.

[0081] In this embodiment, the product influence prediction method includes the following steps:

[0082] Step S10: Obtain the purchasing user information corresponding to the upstream product chain in the product matrix resource.

[0083] It should be noted that the execution subject in this embodiment can be a device with a product impact prediction function, such as a server, a smart phone, a notebook, a computer, and a tablet, etc., and can also be other product impact prediction devices that can achieve the same or similar functions, and this embodiment does not limit this. Here, the above-mentioned computer will be used as an example to illustrate this embodiment and the following embodiments.

[0084] It is understandable that product matrix resources may refer to data information corresponding to a bunch of software products or other physical products made by an enterprise or company. The product matrix may be a matrix relationship composed of products contained in the upper and lower product chains, such as mobile phone software, PC software or hardware products. Since there are intrinsic connections between businesses and resources between products, the product matrix relationship constructed based on the connections between the above products is called a product matrix. Therefore, product matrix resources contain data information corresponding to various types of software products or other physical products. The data information may include product name, user information, product type and other information.

[0085] It should be understood that the purchased user information may refer to the information corresponding to the traffic users acquired by the enterprise at the cost of initial investment. The traffic users refer to the users used to attract more users. The traffic users can accurately locate more target users through Internet advertising investment for promotion.

[0086] In the specific implementation, the product matrix resources of the target enterprise can be obtained through historical data information and real-time data information, and the buying user information of the upstream product chain in the multiple product lines existing in the product matrix resources can be obtained.

[0087] Step S20: Perform multi-dimensional information statistics on the buying volume user information according to preset impact factor dimensions to obtain impact information of the target dimension.

[0088] It should be noted that the preset influencing factor dimension refers to the key influencing factors set in advance for judging the comprehensive impact of upstream products on downstream products. The key influencing factors include influencing factors of multiple dimensions, and the influencing factors include three aspects: volume, quality and income. By reasonably decomposing the influencing factors, clarifying the key influencing factors, and making a reasonable prediction of the overall impact, it is helpful to make quantitative guidance on the overall product matrix resource allocation.

[0089] It can be understood that the impact information is determined based on the information corresponding to the dimensions required to evaluate the impact contained in the key influencing factors. The target dimensions include volume dimensions and quality dimensions. In order to reduce the amount of data processing and data interference, the impact factor of income is eliminated and the impact information corresponding to the volume dimension and quality dimension is used as the key data for later data evaluation.

[0090] In the specific implementation, multi-dimensional information statistics of the purchasing user information are performed through the preset influencing factor dimension to obtain the impact information of the three dimensions of volume, quality and income. However, in order to reduce the interference of the impact information of the income dimension on the overall impact, the impact information of the income dimension is eliminated to obtain the impact information corresponding to the volume and quality.

[0091] In this embodiment, before step S20, it also includes: determining the traffic-driving user information of the upstream product chain according to a preset statistical caliber and the buying user information; and determining the downstream product chain corresponding to the upstream product chain according to the traffic-driving user information.

[0092] It should be noted that in order to clarify which upstream product has generated user contribution to the downstream product, the correspondence between the upstream and downstream products can be determined through a preset statistical caliber. The preset statistical caliber can be based on the user information of the upstream product line buying volume as the data source, and statistics are made based on the payment channels on the delivery side; at the same time, based on internal channels, it is judged that the upstream product diverts users with volume, and then it is clarified which upstream product line has generated user contribution to the downstream product.

[0093] It is understandable that the information on users with traffic refers to the upstream products obtaining users who buy traffic through the paid channels on the delivery side, and then diverting traffic based on the users who buy traffic, and collecting statistics on the data of users with traffic, so as to obtain the information on users with traffic. Based on the information on users with traffic, it is possible to clarify the user contribution of the products in the upstream product line to the downstream products, thereby clarifying the corresponding relationship between the upstream and downstream product chains, so as to facilitate the estimation of the value of the downstream product chain in the later stage.

[0094] In the specific implementation, the user information of the upstream product chain with traffic diversion is determined according to the preset statistical caliber and the user information of the purchasing volume; and the downstream product chain corresponding to the upstream product chain is determined according to the user information of the purchasing volume.

[0095] Step S30: performing an influence prediction on the downstream product chain corresponding to the upstream product chain according to the influence information to obtain an influence prediction result.

[0096] It should be noted that the impact information corresponding to the volume dimension and the impact information corresponding to the quality dimension are used to predict the impact of the downstream products corresponding to the upstream product chain to obtain the impact prediction result.

[0097] It should be understood that the impact prediction results include information such as the new users corresponding to the downstream product chain and the average daily and monthly active days per person.

[0098] In the specific implementation, the impact information of the target dimension corresponding to the upstream product chain is used to predict the impact of the downstream product chain, and the information such as the newly added users and the daily and monthly average active days corresponding to the downstream product chain is obtained. Through the multi-dimensional judgment of the impact, the value between the product matrix is ​​more sourced and clear. While measuring the value of the upstream product itself, it is also clear to understand the value contribution of the existence of the upstream product to other downstream products, and there is data support in the relationship chain.

[0099] This embodiment obtains the user information of the purchase volume corresponding to the upstream product chain in the product matrix resources; performs multi-dimensional information statistics on the user information of the purchase volume according to the preset impact factor dimension to obtain the impact information of the target dimension; performs an impact prediction on the downstream product chain corresponding to the upstream product chain according to the impact information to obtain the impact prediction result. Since this embodiment performs multi-dimensional information statistics on the user information of the purchase volume corresponding to the upstream product chain according to the preset impact factor dimension, and predicts the impact of the downstream product chain according to the impact information obtained by the statistics, compared with the existing technology that requires a lot of manpower and time costs to perform statistics manually, it is impossible to scientifically and reasonably evaluate the value of a single product under the product matrix chain to other product lines, and it is impossible to clarify the impact of upstream products on downstream products. This embodiment achieves scientific and reasonable evaluation of the contribution of a single product under the product matrix chain to other product lines from a global perspective while measuring the value of the single product itself, and clarifies the impact of upstream products on downstream products, so as to maximize the value under the product matrix.

[0100] Reference Figure 3 , Figure 3 This is a flow chart of the second embodiment of the product influence prediction method of the present invention. Figure 2 The first embodiment shown provides a second embodiment of the product influence prediction method of the present invention.

[0101] In this embodiment, the step S20 further includes:

[0102] Step S201: statistics are collected on the purchase volume user information according to the volume dimension to obtain the product new user quantity information corresponding to the volume dimension.

[0103] It should be noted that the volume dimension may be a statistical dimension for annual conversion users, where the annual conversion users refer to the number of new users introduced to the downstream one year after the upstream paying users.

[0104] It is understandable that the information on the number of new users of the product is determined by the number of new downstream users counted in the volume dimension and the user information corresponding to the new users.

[0105] Step S202: statistics are collected on the volume-buying user information according to the quality dimension to obtain the product active days corresponding to the quality dimension.

[0106] It should be noted that the quality dimension may be a statistical dimension for the average monthly active days per capita, and the average monthly active days per capita may refer to the average active days per capita of users imported by upstream paying users into the downstream business line in one month.

[0107] It is understandable that the product active days are obtained by counting the daily traffic of downstream product line users counted in the quality dimension and the average monthly active days of the downstream product line users.

[0108] Step S203: Determine the impact information based on the information on the number of new users of the product and the number of active days of the product.

[0109] In a specific implementation, the impact information is determined by statistically analyzing the information on the number of new product users corresponding to the volume dimension and the number of active days of the product. The information on the number of new product users can be data for the next year or the next few months, with the first month being the actual value, and subsequent data can be predicted through the model.

[0110] Furthermore, the step S203 also includes: counting the information of the number of new users of the product according to a preset statistical period to obtain a first statistical result; counting the number of active days of the product according to the preset statistical period to obtain a second statistical result; and determining the impact information based on the first statistical result and the second statistical result.

[0111] It should be noted that the preset period may be a pre-set period for statistical data, the period may be selected or customized, and the period may include time periods such as days, months, and years. The first statistical result may be to classify and count the information on the number of new product users for the upstream product chain according to the preset period, and obtain the information on the number of new product users counted in each period.

[0112] It is understandable that the second statistical result may be the product active days information obtained by classifying and counting the product active days for the upstream product chain according to the preset period.

[0113] In a specific implementation, the first statistical result and the second statistical result are obtained by collecting statistics on the number of new product users and the number of active days of the product in the upstream paid new information corresponding to the upstream product chain according to a preset period. Then, the impact information of the upstream product chain is determined based on the first statistical result and the second statistical result.

[0114] In this embodiment, the step S30 further includes:

[0115] Step S301: Determine the comprehensive impact of the downstream product chain corresponding to the target period according to the preset statistical logic, the first statistical result and the second statistical result.

[0116] It should be noted that the preset statistical logic is a pre-set statistical logic for determining the influence of upstream products on downstream products. The logic can calculate the comprehensive influence on downstream products based on the product's new user information contained in the first statistical result and the product's active days in the second statistical result.

[0117] It is understandable that the comprehensive impact is the impact generated by integrating the impact information of the two dimensions of volume and quality. The target period can be a period for statistical calculation in months.

[0118] In a specific implementation, the comprehensive influence of the downstream product chain corresponding to the target period is determined by a preset statistical logic, the first statistical result and the second statistical result.

[0119] Furthermore, the step S301 also includes: determining the new user information of the diversion corresponding to the volume dimension of the downstream product chain within the target period according to the preset LR model and the first statistical result; determining the average number of active days of diversion per capita corresponding to the quality dimension of the downstream product chain according to the second statistical result; and determining the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the new user information of the diversion and the average number of active days of diversion per capita.

[0120] It should be noted that in order to improve the accuracy of real-time data analysis, the LR model is pre-built to predict the new user information of the diversion. The LR (Logistic Regression) model is a commonly used classification algorithm that can be used for binary classification problems. In specific applications, the predicted data is pre-processed and predicted based on the pre-processed data to obtain the predicted classification results. When predicting the new user information of the diversion, the time dimension can be used and time series variables can be added for prediction, so that when analyzing real-time data, data in future periods can be predicted.

[0121] It is understandable that the average active days per capita of traffic diversion corresponding to the quality dimension of the downstream product chain is determined based on the number of new paying users of the upstream product within a preset period contained in the second statistical result.

[0122] In the specific implementation, the preset LR model is used to predict the impact of the new paid additions of the upstream products on the new downstream traffic according to the time dimension, to obtain the information of the new traffic diversion users, and based on the average number of active days per person of the daily traffic diversion users of the upstream products in the downstream product chain for one month, the comprehensive impact of the downstream product chain corresponding to the target period is determined based on the preset statistical logic, the new traffic diversion user information and the average number of active days per person of the traffic diversion.

[0123] Step S302: Based on a preset time series model and the comprehensive influence, an influence prediction is performed on the downstream product chain corresponding to the upstream product chain to obtain an influence prediction result.

[0124] It should be noted that the preset time series model can be a pre-set model for predicting data in a future time period based on the time information in the historical data. The model can be an ARIMA model, which is a model based on autoregression, difference and moving average, which can be used to process time series data with seasonality and trend. The ARIMA model can be composed of three parameters: autoregression coefficient (AR), difference coefficient (I) and moving average coefficient (MA). By adjusting the above three parameters, the optimal ARIMA model can be obtained to predict the time series data.

[0125] It is understandable that, in this embodiment, the influence of the downstream product chain corresponding to the upstream product chain in the future period is predicted by using a preset time series model and a comprehensive influence degree to obtain an influence prediction result.

[0126] This embodiment obtains the user information of the purchase volume corresponding to the upstream product chain in the product matrix resources; performs multi-dimensional information statistics on the user information of the purchase volume according to the preset impact factor dimension to obtain the impact information of the target dimension; performs an impact prediction on the downstream product chain corresponding to the upstream product chain according to the impact information to obtain the impact prediction result. Since this embodiment performs multi-dimensional information statistics on the user information of the purchase volume corresponding to the upstream product chain according to the preset impact factor dimension, and predicts the impact of the downstream product chain according to the impact information obtained by the statistics, compared with the existing technology that requires a lot of manpower and time costs to perform statistics manually, it is impossible to scientifically and reasonably evaluate the value of a single product under the product matrix chain to other product lines, and it is impossible to clarify the impact of upstream products on downstream products. This embodiment achieves scientific and reasonable evaluation of the contribution of a single product under the product matrix chain to other product lines from a global perspective while measuring the value of the single product itself, and clarifies the impact of upstream products on downstream products, so as to maximize the value under the product matrix.

[0127] Based on the above Figure 3 The second embodiment shown provides a third embodiment of the product influence prediction method of the present invention.

[0128] In this embodiment, the step of determining the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the new user information of the diverted traffic, and the average active days of the diverted traffic includes: determining the daily comprehensive influence corresponding to the daily new paying users according to the preset statistical logic, the new user information of the diverted traffic, and the average active days of the diverted traffic; determining the monthly comprehensive influence corresponding to the monthly new paying users according to the preset statistical logic, the new user information of the diverted traffic, and the average active days of the diverted traffic; determining the comprehensive influence of the downstream product chain according to the daily comprehensive influence and the monthly comprehensive influence.

[0129] It should be noted that the preset statistical logic includes the comprehensive impact statistical logic of new paying users (buying users) of upstream products in daily and monthly cycles.

[0130] In the specific implementation, the calculation method of the daily comprehensive influence includes: daily new paying users = annual conversion rate * average monthly active days per person, the annual conversion rate refers to the proportion of new downstream users introduced by upstream paying users within one year; daily comprehensive influence = (annual new users * average monthly active days per person) / daily new paying users.

[0131] It should be noted that conversion users are users acquired by upstream products through paid channels and converted in downstream products. Due to the lag in user behavior, it may take some time for users to be converted in downstream products after they are newly added in the upstream on the same day. The time window involves conversions in different time dimensions, namely daily conversion users, monthly conversion users, and annual conversion users, that is, users acquired by the upstream, and the cumulative conversion users in downstream products in different windows of day / month / year.

[0132] It is understandable that the conversion rate is the probability of users acquired through paid channels upstream to convert in the downstream. Due to the lag of user behavior, it may take some time for users to convert in downstream products after they are newly added upstream on the same day, so it is necessary to calculate according to different time windows. That is, the cumulative conversions of users newly added in the upstream paid channels on the same day in the next day, month, and year.

[0133] In the specific implementation, after counting the new paying users of the upstream products on a daily basis, it is necessary to predict the impact of the downstream products corresponding to the upstream products based on the impact information corresponding to the new paying users. That is, the statistical logic steps are daily comprehensive impact = (annual converted users * average monthly active days per person) / daily new paying users = conversion rate * average monthly active days per person.

[0134] Furthermore, the calculation method of the monthly comprehensive influence includes: determining the annual new users of the monthly new paying users based on the daily average annual conversion rate and the monthly new paying users, where annual new users = monthly new paying users * daily average annual conversion rate; determining the monthly comprehensive influence based on the daily average annual conversion rate and the daily average monthly active days per person, where monthly comprehensive influence = daily average annual conversion rate * daily average monthly active days per person.

[0135] It should be noted that from the perspective of the formula, daily conversion rate = downstream single-day converted users / upstream single-day new paying users; monthly conversion rate = downstream 30-day converted users / upstream single-day new paying users; annual conversion rate = downstream 365-day cumulative converted users / upstream single-day new paying users

[0136] It can be understood that the daily average annual conversion rate refers to the daily average of the annual conversion rates of multiple single days. For example, the daily average annual conversion rate from 20230101 to 20230110 = avg (1-day annual conversion rate + 2-day annual conversion rate = 3-day annual conversion rate + 4-day annual conversion rate + 5-day annual conversion rate + 6-day annual conversion rate + 7-day annual conversion rate + 8-day annual conversion rate + 9-day annual conversion rate + 10-day annual conversion rate).

[0137] In the specific implementation, after counting the new paying users of the upstream products on a monthly basis, it is necessary to predict the impact of the downstream products corresponding to the upstream products based on the impact information corresponding to the new paying users. That is, the statistical logic steps are to first calculate the daily average annual conversion rate and the monthly new paying users, and then calculate the annual conversion users of the monthly new paying users: annual conversion users = monthly new paying users * daily average annual conversion rate, and calculate the monthly comprehensive impact based on the daily average annual conversion rate and the daily average monthly active days per person: monthly comprehensive impact = daily average annual conversion rate * daily average monthly active days per person.

[0138] Furthermore, after step S30, it also includes: generating a traffic diversion ecological map between product matrices according to the influence prediction result; generating a traffic diversion trend map corresponding to the volume dimension and the quality dimension according to a preset time series model and the traffic diversion ecological map.

[0139] It should be noted that the diversion ecological map is generated according to the corresponding relationship between the upstream and downstream product chains contained in the impact prediction results and the influence of the existence of the upstream product on other downstream products, and the diversion trend map corresponding to the volume dimension and the quality dimension is generated according to the preset time series model and the diversion ecological map. The preset time series model can be a model trained based on the ARIMA model. For details, please refer to Figure 4 The paid user influence diagram shown in the figure includes a traffic diversion ecology diagram and traffic diversion trend diagrams corresponding to the volume dimension and quality dimension. Among them, mobile guard, mobile assistant and mobile browser are used as examples for explanation.

[0140] Furthermore, after step 30, it also includes: generating a business impact analysis chart based on the newly added user information of the diversion, the average active days of the diversion users, the comprehensive impact and the impact prediction result, and displaying the business impact analysis chart.

[0141] It should be noted that in order to generate quantitative values ​​of the overall impact from the perspective of volume and quality, and at the same time have a clear understanding of the upstream volume diversion of the product, a business impact analysis chart can be generated based on the information of newly added users, the average number of active days per person in the diversion, the comprehensive impact and the impact prediction results, and the business impact analysis chart can be displayed. The business impact analysis chart includes an impact analysis table and a trend chart.

[0142] Understandably, one can refer to Figure 5The business impact analysis diagram shown in the figure takes the upstream product chain: mobile phone guard and the downstream product chain: film and television encyclopedia as examples, and represents the impact analysis results and trend chart for one day, including the overall impact (comprehensive impact) of the three types of products in the downstream product chain, the cumulative converted users (i.e. the information of newly added users diverted) are represented in a table, and the number of daily active users (average active days per person diverted) and the number of new users (information of newly added users diverted) are represented according to the trend chart based on the volume dimension and quality dimension.

[0143] In the specific implementation, in terms of the number of users and budget allocation of downstream products, this solution can clearly understand the value of upstream products to downstream products, and downstream products can also clearly understand the linkage impact of upstream products in terms of volume and quality. When downstream products set their own DAU goals and purchase volume budgets, they can achieve a clear breakdown of user composition and user volume, which can play a certain guiding role in internal and external budget allocation.

[0144] This embodiment obtains the user information of the purchase volume corresponding to the upstream product chain in the product matrix resources; performs multi-dimensional information statistics on the user information of the purchase volume according to the preset impact factor dimension to obtain the impact information of the target dimension; performs an impact prediction on the downstream product chain corresponding to the upstream product chain according to the impact information to obtain the impact prediction result. Since this embodiment performs multi-dimensional information statistics on the user information of the purchase volume corresponding to the upstream product chain according to the preset impact factor dimension, and predicts the impact of the downstream product chain according to the impact information obtained by the statistics, compared with the existing technology that requires a lot of manpower and time costs to perform statistics manually, it is impossible to scientifically and reasonably evaluate the value of a single product under the product matrix chain to other product lines, and it is impossible to clarify the impact of upstream products on downstream products. This embodiment achieves scientific and reasonable evaluation of the contribution of a single product under the product matrix chain to other product lines from a global perspective while measuring the value of the single product itself, and clarifies the impact of upstream products on downstream products, so as to maximize the value under the product matrix.

[0145] In addition, to achieve the above objectives, the present invention also proposes a storage medium, on which a product influence prediction program is stored, and when the product influence prediction program is executed by a processor, the steps of the product influence prediction method described above are implemented.

[0146] Reference Figure 6 , Figure 6 This is a structural block diagram of the first embodiment of the product influence prediction device of the present invention.

[0147] like Figure 6 As shown, the product influence prediction device proposed in the embodiment of the present invention includes:

[0148] Information acquisition module 10, used to obtain the buying volume user information corresponding to the upstream product chain in the product matrix resource;

[0149] An information determination module 20 is used to perform multi-dimensional information statistics on the user information of the purchased volume according to preset impact factor dimensions to obtain impact information of the target dimension;

[0150] The influence prediction module 30 is used to predict the influence of the downstream product chain corresponding to the upstream product chain according to the influence information to obtain an influence prediction result.

[0151] This embodiment obtains the user information of the purchase volume corresponding to the upstream product chain in the product matrix resources; performs multi-dimensional information statistics on the user information of the purchase volume according to the preset impact factor dimension to obtain the impact information of the target dimension; performs an impact prediction on the downstream product chain corresponding to the upstream product chain according to the impact information to obtain the impact prediction result. Since this embodiment performs multi-dimensional information statistics on the user information of the purchase volume corresponding to the upstream product chain according to the preset impact factor dimension, and predicts the impact of the downstream product chain according to the impact information obtained by the statistics, compared with the existing technology that requires a lot of manpower and time costs to perform statistics manually, it is impossible to scientifically and reasonably evaluate the value of a single product under the product matrix chain to other product lines, and it is impossible to clarify the impact of upstream products on downstream products. This embodiment achieves scientific and reasonable evaluation of the contribution of a single product under the product matrix chain to other product lines from a global perspective while measuring the value of the single product itself, and clarifies the impact of upstream products on downstream products, so as to maximize the value under the product matrix.

[0152] Furthermore, the product influence prediction device further includes: a product chain determination module;

[0153] The product chain determination module is used to determine the traffic volume user information of the upstream product chain according to the preset statistical caliber and the purchase volume user information;

[0154] The product chain determination module is further used to determine the downstream product chain corresponding to the upstream product chain according to the guide belt quantity user information.

[0155] Furthermore, the preset influencing factor dimension includes a volume dimension and a quality dimension, and the information determination module 10 is further used to count the user information of the purchased volume according to the volume dimension to obtain the product new user quantity information corresponding to the volume dimension;

[0156] The information determination module 10 is further used to collect statistics on the user information of the purchased volume according to the quality dimension to obtain the number of product active days corresponding to the quality dimension;

[0157] The information determination module 10 is further used to determine the impact information based on the information on the number of new users of the product and the number of active days of the product.

[0158] Furthermore, the information determination module 10 is further used to collect statistics on the amount of new users of the product according to a preset statistical period to obtain a first statistical result;

[0159] The information determination module 10 is further used to count the number of active days of the product according to the preset statistical period to obtain a second statistical result;

[0160] The information determination module 10 is further configured to determine the impact information according to the first statistical result and the second statistical result.

[0161] Furthermore, the influence prediction module 30 is further used to determine the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the first statistical result and the second statistical result;

[0162] The influence prediction module 30 is further used to predict the influence of the downstream product chain corresponding to the upstream product chain based on a preset time series model and the comprehensive influence, so as to obtain an influence prediction result.

[0163] Furthermore, the influence prediction module 30 is further used to determine the newly added user information of the downstream product chain corresponding to the volume dimension within the target period according to the preset LR model and the first statistical result;

[0164] The influence prediction module 30 is further used to determine the average active days per traffic diversion person corresponding to the quality dimension of the downstream product chain according to the second statistical result;

[0165] The influence prediction module 30 is also used to determine the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the information of the newly added users of the diversion and the average active days of the diversion users.

[0166] Furthermore, the influence prediction module 30 is further used to determine the daily comprehensive influence corresponding to the daily newly added paying users according to the preset statistical logic, the newly added user information of the diversion and the average active days of the diversion;

[0167] The influence prediction module 30 is further used to determine the monthly comprehensive influence corresponding to the monthly newly added paying users according to the preset statistical logic, the newly added user information of the diversion and the average active days of the diversion users;

[0168] The influence prediction module 30 is further used to determine the comprehensive influence of the downstream product chain according to the daily comprehensive influence and the monthly comprehensive influence.

[0169] Furthermore, the product influence prediction device also includes a flow diagram generation module;

[0170] The flow diversion graph generation module is used to generate a flow diversion ecological graph between product matrices according to the influence prediction result;

[0171] The diversion map generation module is also used to generate a diversion trend map corresponding to the volume dimension and the quality dimension according to the preset time series model and the diversion ecological map.

[0172] Furthermore, the traffic diversion map generation module is also used to generate a business impact analysis map based on the newly added user information of the diversion, the average active days of the diversion users, the comprehensive impact and the impact prediction results, and display the business impact analysis map.

[0173] Other embodiments or specific implementations of the product influence prediction device of the present invention can refer to the above-mentioned method embodiments and will not be described in detail here.

[0174] The present invention provides A1, a product influence prediction method, the product influence prediction method comprising the following steps:

[0175] Obtain the purchasing user information corresponding to the upstream product chain in the product matrix resources;

[0176] Perform multi-dimensional information statistics on the user information of the purchased volume according to the preset impact factor dimension to obtain the impact information of the target dimension;

[0177] An influence degree prediction is performed on the downstream product chain corresponding to the upstream product chain according to the influence information to obtain an influence degree prediction result.

[0178] A2. The product influence prediction method as described in A1, before the step of performing multi-dimensional information statistics on the buying volume user information according to the preset influence evaluation dimension to obtain the influence information of the target dimension, further comprises:

[0179] Determine the traffic-driving user information of the upstream product chain according to the preset statistical caliber and the buying user information;

[0180] The downstream product chain corresponding to the upstream product chain is determined according to the guide belt quantity user information.

[0181] A3. The product influence prediction method as described in A2, wherein the preset influence factor dimensions include a volume dimension and a quality dimension, and the step of performing multi-dimensional information statistics on the user information of the purchased volume according to the preset influence factor dimensions to obtain the influence information of the target dimension includes:

[0182] The buying volume user information is counted according to the volume dimension to obtain the product new user volume information corresponding to the volume dimension;

[0183] The buying volume user information is counted according to the quality dimension to obtain the number of product active days corresponding to the quality dimension;

[0184] The impact information is determined based on the information on the number of new users of the product and the number of active days of the product.

[0185] A4. The product influence prediction method as described in A3, wherein the step of determining the influence information based on the information on the number of new users of the product and the number of active days of the product comprises:

[0186] Counting the amount of new users of the product according to a preset statistical period to obtain a first statistical result;

[0187] Counting the number of active days of the product according to the preset statistical period to obtain a second statistical result;

[0188] Influence information is determined according to the first statistical result and the second statistical result.

[0189] A5. The product influence prediction method as described in A1 to A4, wherein the step of performing influence prediction on the downstream product chain corresponding to the upstream product chain according to the influence information to obtain the influence prediction result comprises:

[0190] Determine the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the first statistical result and the second statistical result;

[0191] Based on the preset time series model and the comprehensive influence, an influence prediction is performed on the downstream product chain corresponding to the upstream product chain to obtain an influence prediction result.

[0192] A6. The product influence prediction method as described in A5, wherein the step of determining the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the first statistical result and the second statistical result comprises:

[0193] Determine the newly added user information of the downstream product chain corresponding to the volume dimension within the target period according to the preset LR model and the first statistical result;

[0194] Determine the average active days per traffic diverter corresponding to the quality dimension of the downstream product chain according to the second statistical result;

[0195] The comprehensive influence of the downstream product chain corresponding to the target period is determined according to the preset statistical logic, the newly added user information of the diversion and the average active days of the diversion users.

[0196] A7. The product influence prediction method as described in A6, wherein the step of determining the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the newly added user information of the diversion, and the average number of active days per person of the diversion includes:

[0197] Determine the daily comprehensive impact of newly added paying users based on the preset statistical logic, the newly added user information of the diversion, and the average number of active days per person of the diversion;

[0198] Determine the monthly comprehensive impact corresponding to the monthly newly added paying users according to the preset statistical logic, the newly added user information of the diversion and the average active days of the diversion users;

[0199] The comprehensive impact of the downstream product chain is determined according to the daily comprehensive impact and the monthly comprehensive impact.

[0200] A8. The product influence prediction method as described in A1, wherein after the step of performing influence prediction on the downstream product chain corresponding to the upstream product chain according to the influence information and obtaining the influence prediction result, the method further comprises:

[0201] Generate a traffic diversion ecological map between product matrices according to the impact prediction results;

[0202] A diversion trend graph corresponding to the volume dimension and the quality dimension is generated according to the preset time series model and the diversion ecological graph.

[0203] A9. The product influence prediction method as described in A7, wherein after the step of performing influence prediction on the downstream product chain corresponding to the upstream product chain according to the influence information and obtaining the influence prediction result, the method further comprises:

[0204] A business impact analysis graph is generated based on the newly added user information of the diversion, the average active days of the diversion users, the comprehensive impact and the impact prediction result, and the business impact analysis graph is displayed.

[0205] A10. In the product impact prediction method described in A7, the daily comprehensive impact is calculated by:

[0206] Daily new paying users = annual conversion rate * average monthly active days per person. The annual conversion rate refers to the proportion of new downstream users introduced by upstream paying users within one year.

[0207] Daily comprehensive impact = (annual new users * average monthly active days per person) / daily new paying users.

[0208] A11. The product influence prediction method as described in any one of A10, wherein the calculation method of the monthly comprehensive influence comprises:

[0209] Determine the annual new users of the monthly new paying users according to the daily average annual conversion rate and the monthly new paying users, where annual new users = monthly new paying users * daily average annual conversion rate;

[0210] The monthly comprehensive influence is determined based on the daily average annual conversion rate and the daily average monthly active days per person, where the monthly comprehensive influence = daily average annual conversion rate * daily average monthly active days per person.

[0211] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system 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, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0212] The serial numbers of the embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. In a unit claim that lists several means, several of these means may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order and these words may be interpreted as names.

[0213] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0214] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A product influence prediction method, characterized in that: The product influence prediction method comprises the following steps: Obtain the purchasing user information corresponding to the upstream product chain in the product matrix resources; Perform multi-dimensional information statistics on the user information of the purchased volume according to the preset impact factor dimension to obtain the impact information of the target dimension; An influence degree prediction is performed on the downstream product chain corresponding to the upstream product chain according to the influence information to obtain an influence degree prediction result.

2. The product impact prediction method according to claim 1, characterized in that: Before the step of performing multi-dimensional information statistics on the user information of the purchased volume according to the preset influence evaluation dimension to obtain the influence information of the target dimension, the step further includes: Determine the traffic-driving user information of the upstream product chain according to the preset statistical caliber and the buying user information; The downstream product chain corresponding to the upstream product chain is determined according to the guide belt quantity user information.

3. The product impact prediction method according to claim 2, characterized in that: The preset impact factor dimensions include a volume dimension and a quality dimension. The step of performing multi-dimensional information statistics on the volume-buying user information according to the preset impact factor dimensions to obtain impact information of the target dimension includes: The buying volume user information is counted according to the volume dimension to obtain the product new user volume information corresponding to the volume dimension; The buying volume user information is counted according to the quality dimension to obtain the number of product active days corresponding to the quality dimension; The impact information is determined based on the information on the number of new users of the product and the number of active days of the product.

4. The product impact prediction method according to claim 3, characterized in that: The step of determining the influence information according to the information of the number of new users of the product and the number of active days of the product includes: Counting the amount of new users of the product according to a preset statistical period to obtain a first statistical result; Counting the number of active days of the product according to the preset statistical period to obtain a second statistical result; Influence information is determined according to the first statistical result and the second statistical result.

5. The product impact prediction method according to any one of claims 1 to 4, characterized in that: The step of performing an influence prediction on the downstream product chain corresponding to the upstream product chain according to the influence information to obtain an influence prediction result comprises: Determine the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the first statistical result and the second statistical result; Based on the preset time series model and the comprehensive influence, an influence prediction is performed on the downstream product chain corresponding to the upstream product chain to obtain an influence prediction result.

6. The product impact prediction method according to claim 5, characterized in that: The step of determining the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the first statistical result and the second statistical result includes: Determine the newly added user information of the downstream product chain corresponding to the volume dimension within the target period according to the preset LR model and the first statistical result; Determine the average active days per traffic diverter corresponding to the quality dimension of the downstream product chain according to the second statistical result; The comprehensive influence of the downstream product chain corresponding to the target period is determined according to the preset statistical logic, the newly added user information of the diversion and the average active days of the diversion users.

7. The product impact prediction method according to claim 6, characterized in that: The step of determining the comprehensive influence of the downstream product chain corresponding to the target period according to the preset statistical logic, the newly added user information of the diversion, and the average number of active days per person of the diversion includes: Determine the daily comprehensive impact of newly added paying users based on the preset statistical logic, the newly added user information of the diversion, and the average number of active days per person of the diversion; Determine the monthly comprehensive impact corresponding to the monthly newly added paying users according to the preset statistical logic, the newly added user information of the diversion and the average active days of the diversion users; The comprehensive impact of the downstream product chain is determined according to the daily comprehensive impact and the monthly comprehensive impact.

8. A product impact prediction device, characterized in that: The product impact prediction device includes: a memory, a processor, and a product impact prediction program stored in the memory and executable on the processor. When the product impact prediction program is executed by the processor, the product impact prediction method according to any one of claims 1 to 7 is implemented.

9. A storage medium, characterized in that: The storage medium stores a product impact prediction program, and when the product impact prediction program is executed by the processor, the product impact prediction method according to any one of claims 1 to 7 is implemented.

10. A product influence prediction device, characterized in that: The product impact prediction includes: The information acquisition module is used to obtain the purchasing user information corresponding to the upstream product chain in the product matrix resources; An information determination module, used to perform multi-dimensional information statistics on the user information of the purchased volume according to preset impact factor dimensions to obtain impact information of the target dimension; The influence prediction module is used to predict the influence of the downstream product chain corresponding to the upstream product chain according to the influence information to obtain the influence prediction result.

Images