CN108229804A - Brand promotion project management method, device, terminal device and storage medium - Google Patents
Brand promotion project management method, device, terminal device and storage medium Download PDFInfo
- Publication number
- CN108229804A CN108229804A CN201711429863.0A CN201711429863A CN108229804A CN 108229804 A CN108229804 A CN 108229804A CN 201711429863 A CN201711429863 A CN 201711429863A CN 108229804 A CN108229804 A CN 108229804A
- Authority
- CN
- China
- Prior art keywords
- project
- kpi
- current
- information
- acquiring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 53
- 238000003860 storage Methods 0.000 title abstract description 15
- 238000013210 evaluation model Methods 0.000 claims description 93
- 238000013527 convolutional neural network Methods 0.000 claims description 53
- 238000000034 method Methods 0.000 claims description 40
- 238000004364 calculation method Methods 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 22
- 238000010586 diagram Methods 0.000 claims description 19
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000011176 pooling Methods 0.000 claims description 11
- 239000000654 additive Substances 0.000 claims description 8
- 230000000996 additive effect Effects 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 230000001737 promoting effect Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 12
- 238000007689 inspection Methods 0.000 abstract 3
- 230000008569 process Effects 0.000 description 27
- 230000035945 sensitivity Effects 0.000 description 11
- 238000013461 design Methods 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000007480 spreading Effects 0.000 description 2
- 238000003892 spreading Methods 0.000 description 2
- 241000287196 Asthenes Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of brand promotion project management method, device, terminal device and storage mediums.The brand promotion project management method obtains project acceptance inspection information, and the project acceptance inspection information includes item id, project channel and at least two current project indexs；Based on the project channel, corresponding KPI assessment models are obtained；Based on the KPI assessment models and at least two current project indexs, current KPI value is obtained；Based on the item id, the target KPI value of corresponding brand promotion project is obtained；Based on the current KPI value and the target KPI value, the project acceptance inspection result of the brand promotion project is obtained.The brand promotion project management method can intuitively, effectively evaluate the completion effect of brand promotion project.
Description
Technical Field
The invention relates to the field of project management, in particular to a brand propaganda project management method, a brand propaganda project management device, terminal equipment and a storage medium.
Background
Project management generally includes stages of project initiation, project establishment, project execution and project acceptance, including but not limited to brand promotion project management. In the brand promotion project management, project starting refers to a process of making a decision or plan of a brand promotion project, project establishment refers to a process of drawing up a work target or plan of the brand promotion project according to the made decision or plan, project execution refers to a process of executing the brand promotion project according to the drawn up work target or plan, and project acceptance refers to a process of accepting the execution condition and effect of the brand promotion project. In the project acceptance stage of the brand propaganda project, due to the fact that project channels (namely the propagation modes of the brand propaganda) of the brand propaganda project are different, corresponding project indexes (such as environmental interference degree, audience concentration degree and the like) are different, moreover, a plurality of project indexes collected in the same project channel are mutually influenced, the completion effect of the brand propaganda project cannot be evaluated, and therefore whether the brand propaganda project meets the expectation of project establishment cannot be evaluated visually.
Disclosure of Invention
The embodiment of the invention provides a brand propaganda project management method, which aims to solve the problem that the completion effect of a brand propaganda project cannot be visually evaluated in the current brand propaganda project management process.
In a first aspect, an embodiment of the present invention provides a brand promotion item management method, including:
acquiring project acceptance information, wherein the project acceptance information comprises a project ID, a project channel and at least two current project indexes;
acquiring a corresponding KPI (Key performance indicator) evaluation model based on the project channel;
acquiring a current KPI value based on the KPI evaluation model and at least two current project indexes;
acquiring a target KPI value of a corresponding brand propaganda project based on the project ID;
and acquiring a project acceptance result of the brand propaganda project based on the current KPI value and the target KPI value.
In a second aspect, an embodiment of the present invention provides a brand promotion item management apparatus, including:
the project acceptance information acquisition module is used for acquiring project acceptance information, and the project acceptance information comprises a project ID, a project channel and at least two current project indexes;
the KPI evaluation model acquisition module is used for acquiring a corresponding KPI evaluation model based on the project channel;
a current KPI value obtaining module, configured to obtain a current KPI value based on the KPI evaluation model and at least two current project indicators;
the target KPI value acquisition module is used for acquiring a target KPI value of a corresponding brand propaganda project based on the project ID;
and the project acceptance result acquisition module is used for acquiring a project acceptance result of the brand propaganda project based on the current KPI value and the target KPI value.
In a third aspect, an embodiment of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the brand promotion item management method when executing the computer program.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the brand promotion item management method.
According to the brand propaganda project management method, the brand propaganda project management device, the terminal equipment and the storage medium, project acceptance information is firstly acquired, the project acceptance information comprises a project ID, a project channel and at least two current project indexes, and by acquiring the project acceptance information, a data basis for performing brand propaganda project management is effectively provided. And then acquiring a corresponding KPI evaluation model based on the project channel, acquiring the corresponding KPI evaluation model according to the project channel through the project channel, and providing a proper evaluation model for acquiring the current KPI. And then, acquiring a current KPI value based on the KPI evaluation model and at least two current project indexes, and acquiring the current KPI value by using the KPI evaluation model and the current project indexes, thereby providing an important data basis for acquiring a project acceptance result of the brand propaganda project. And then, based on the project ID, acquiring a target KPI value of the corresponding brand propaganda project, and by acquiring the target KPI value of the corresponding brand propaganda project, the effect of checking whether the brand propaganda project conforms to the expected design on the current KPI value is favorably realized through the target KPI value. And finally, acquiring a project acceptance result of the brand propaganda project based on the current KPI value and the target KPI value, and evaluating the completion condition of the brand propaganda project by comparing the current KPI value with the target KPI value to determine whether the brand propaganda project reaches an expected value, namely, visually evaluating the completion effect of the brand propaganda project by adopting the calculated current KPI value.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
Fig. 1 is a flowchart of a method for managing a brand promotion project according to embodiment 1 of the present invention.
Fig. 2 is a detailed flowchart before step S10 in fig. 1.
Fig. 3 is a specific flowchart of step S11 in fig. 2.
Fig. 4 is a detailed flowchart before step S20 in fig. 1.
Fig. 5 is a specific flowchart of step S22 in fig. 4.
Fig. 6 is another flowchart of a method for managing a brand promotion program according to embodiment 1 of the present invention.
Fig. 7 is a schematic block diagram of a brand promotion item management apparatus according to embodiment 2 of the present invention.
Fig. 8 is a schematic diagram of a terminal device in embodiment 4 of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Fig. 1 shows a flowchart of a method for managing a brand promotion project according to the present embodiment. The brand propaganda project management method can be applied to terminal equipment configured by financial institutions such as banks, insurance and securities and other institutions or other institutions, is used for managing brand propaganda projects, and can be particularly applied to a brand propaganda project management system installed on the terminal equipment. The brand promotion item management system is a system for managing a brand promotion item. The terminal device is a device capable of performing human-computer interaction with a user, and includes, but is not limited to, a computer, a smart phone, a tablet and the like. As shown in fig. 1, the brand promotion item management method includes the steps of:
s10: and acquiring project acceptance information, wherein the project acceptance information comprises a project ID, a project channel and at least two current project indexes.
The project acceptance information refers to information contained in the project acceptance process. The item ID refers to an identification for uniquely identifying the brand promotional item. The item channel refers to a mode of propagandizing and spreading brand propaganda items. The project channel can comprise channels such as outdoor advertisements (such as outdoor large boards, wall-brushing advertisements, LED advertisements, community lamp boxes, subways, buses, buildings, airports, high-speed rails, movie theaters and the like), network advertisements (such as video advertisements, search advertisements, brand image-text advertisements, information flow advertisements and the like), plane advertisements (such as newspaper advertisements, magazine advertisements and the like) and television advertisements (such as television advertisement films, embedded advertisements and the like). The current project index is a project index for measuring the quality of the brand propaganda project corresponding to the project ID. The project index includes a specific dimension and a corresponding numerical value, while the current project index includes the specific dimension and an actual value determined at the time of project acceptance. Project metrics may include specific dimensions such as dissemination breadth (traffic, exposure, volume of release, number of covered people), dissemination depth (geographical location, advertisement duration), cost and effectiveness assessment. Specifically, the project index should be associated with the project channel, for example, when the project channel is an outdoor advertisement, the specific index in the propagation breadth dimension may be the flow of people, the length of the display time, and the like. When the project channel is the network advertisement, specific indexes in the propagation breadth dimension can be the exposure, the frequency of putting and the like, but not indexes such as the flow of people and the display duration of outdoor advertisements in the project channel. It will be appreciated that each project index will depend on the particular project channel and is not necessarily generic across other project channels.
In this embodiment, in the project acceptance stage, the terminal device obtains the project acceptance information, where the project acceptance information includes the project ID, the project channel, and at least two current project indexes, and by obtaining the project acceptance information, the terminal device can provide data support for subsequently obtaining the KPI evaluation model and the current KPI value, and provide basic information for finally obtaining the project acceptance result of the brand promotion project.
In an embodiment, as shown in fig. 2, before acquiring the item acceptance information (i.e., step S10), the method specifically includes the following steps:
s11: and acquiring project establishment information, wherein the project establishment information comprises a project ID, a project type, a project channel and project budget expenditure.
The project establishment information refers to information included in a project establishment process. The item ID refers to an identification for uniquely identifying an item. An item type refers to a particular hierarchical type of the item, such as an item type that is of a large, medium, small, or other hierarchy. The item channel refers to a mode of propagandizing and spreading brand propaganda items. The project budget expenditure refers to an expenditure value preset when the project is established, and is used for estimating the total expenditure required in the whole process of the brand promotion project in advance. In addition, the project establishment information corresponds to the project acceptance information, that is, the project establishment information should also include at least two project indexes, the project indexes are the same as the specific dimensions of the current project indexes, but the numerical values of the project indexes are preset values of project establishment stages rather than actual values of the project acceptance stages.
S12: and acquiring a project expense range and a target KPI calculation table based on the project type and the project channel.
The project expense range refers to an expense range determined according to the project type and the project channel in the project establishment process, and is a judgment index used for judging whether the project budget expense meets the requirement of the project establishment of the corresponding project type. The target KPI calculation table refers to a table used for calculating a target KPI value in a project establishment process. The target KPI value is a KPI value which is determined to be reached by the brand promotion project in the project establishment stage, and is an expected value for evaluating the completion condition of the brand promotion project. Among them, kpi (key performance indicator) is a key performance indicator, and is an evaluation indicator for evaluating the performance of a project.
In this embodiment, if the level of the project type is large and the project channel is an outdoor advertisement, the terminal device searches a project expense range and a target KPI calculation table corresponding to the project type and the project channel according to the obtained project type and the project channel, that is, the terminal device queries the project expense range corresponding to the large level of the obtained project type and queries the target KPI calculation table corresponding to the outdoor advertisement of the obtained project channel. Specifically, the project expense range and the KPI calculation table are stored in the database and are associated with the project type and the project channel, and the corresponding project expense range and the target KPI calculation table can be inquired and obtained through the database inquiry statement, so that the process is simple and convenient.
S13: and if the project budget expenditure is within the project expenditure range, acquiring a target KPI value corresponding to the project ID through the application of project establishment information and based on the target KPI calculation table and the project budget expenditure.
In this embodiment, the application of the project establishment information needs to be checked to determine whether the application condition of the project establishment information is met before the application of the project establishment information passes. Specifically, the project budget expenditure is compared with the project expenditure range, and if the project budget expenditure is in the project expenditure range, the project information is applied through the project; and acquiring a target KPI value corresponding to the project ID according to a target KPI calculation table corresponding to the project channel and project budget expenses. The target KPI value can be obtained by calculating according to a custom set proportion or other KPI calculation modes, and an appropriate calculation mode is selected in a KPI calculation table according to specific conditions.
S14: and if the project budget expenditure is not in the project expenditure range, acquiring prompt information that the project establishment application does not pass.
Specifically, after the project expense range is determined according to the project type and the project channel in the standing application information, if the project budget expense is judged to be out of the project expense range by comparison, the standing application information is judged to be not in accordance with the application condition, and prompt information that the standing application does not pass is displayed on a display interface of the terminal device to prompt a user to re-input the application in accordance with the standing application information.
In one embodiment, in step S11, the project establishment information further includes a project expense information table. The project expense application information refers to specific information for forming project budget expense in the project establishment process. As shown in fig. 3, the acquiring of the project establishment information specifically includes the following steps:
s111: acquiring project expense application information, wherein the project expense application information comprises a current expense subject and a specific expense value.
Specifically, the project expense application information emphasizes specific information such as current expense subjects and specific expense values in the project establishment process. The current expense subject refers to a specific classification category of the expense in the project establishment process, for example, the current expense subject can be subject such as advertisement fee, supplier service fee and propaganda article fee. The specific cost value is the cost that the current cost subject is expected to spend at the project establishment stage.
S112: and if the current expense subject is the standard expense subject, determining a project expense information table based on the current expense subject and the specific expense value.
The standard cost subject is a cost subject set by performing unified aperture management on the cost subject. In this embodiment, when an enterprise owns multiple management subsystems, the apertures of the management subsystems are often not aligned, for example, the apertures of purchasing, finance, business, and the like are not consistent, which may result in failure to support analysis and design of the key performance indicators and subsequent optimization operations, and the standard cost subject is set to solve the above-mentioned problem. If all the various fees of the brand publicity project can be set as three major categories of standard fee subjects, namely advertising fees, supplier service fees and publicity article fees, each major category of standard fee subject is further subdivided into a plurality of minor categories of standard fee subjects, and in the project establishment process, the current fee subject is made to correspond to the minor categories of standard fee subjects. In this embodiment, if the current cost subject is the standard cost subject, the subsequent analysis design and optimization operation of the key performance indicators will not be affected, and the project expense information table may be determined based on the current cost subject and the specific cost value.
S113: and if the current expense subject is not the standard expense subject, converting the current expense subject by adopting a preset project subject conversion table to obtain the corresponding standard expense subject, and determining a project expense information table based on the standard expense subject and the specific expense value.
The preset item subject conversion table is a preset conversion table for converting non-standard cost subjects into standard cost subjects, namely the preset item subject conversion table is used for recording the conversion relationship between the cost subjects used by the current brand propaganda items in the current management subsystem or mechanism and the standard cost subjects, so that the brand propaganda cost apertures of all the brand propaganda items are consistent. For example, media advertisement, media acquirement and brand cooperation of non-standard expense subjects are converted into advertisement fees in corresponding standard expense subjects through conversion relations in a preset project subject conversion table.
In this embodiment, if the current expense subject is not the standard expense subject, a preset project subject conversion table stored in the database needs to be acquired, the current expense subject is converted by using a preset project subject conversion table, the corresponding standard expense subject is acquired, and the project expense information table can be determined based on the standard expense subject and the specific expense value.
S20: and acquiring a corresponding KPI evaluation model based on the project channel.
The KPI evaluation model is an evaluation model for obtaining a KPI value related to a specific index according to the specific index. In this embodiment, the terminal device may obtain, according to the project channel, a KPI evaluation model corresponding to the project channel, and the specific process is to search and call a model file corresponding to the KPI evaluation model stored in a database connected to the terminal device, where the model file refers to a model file form in which the KPI evaluation model is stored in the database. The KPI evaluation models corresponding to different project channels are different, for example, when the project channel is an outdoor advertisement, the acquired KPI evaluation model is a KPI value used for calculating that the project channel is the outdoor advertisement; when the project channel is the network advertisement, the acquired KPI evaluation model is used for calculating the KPI value of the project channel which is the network advertisement. The corresponding KPI evaluation model is obtained through a specific project channel, the evaluation model with very high KPI value calculation accuracy and referenceability on the project channel can be provided, and the KPI evaluation model with reliable and accurate calculation results is provided for subsequent KPI value calculation and acceptance result obtaining.
In one embodiment, as shown in fig. 4, before the step of obtaining the corresponding KPI evaluation model based on the project channel (i.e. step S20), the brand promotion project management method further includes pre-training the KPI evaluation model, where the pre-training the KPI evaluation model specifically includes the following steps:
s21: and acquiring original project information of the same project channel, wherein the original project information comprises an original KPI value and at least two original project indexes.
The original project information refers to project information of a created project, and can be understood as project information in a historical project, and here, the original project information is used as training data to train a KPI evaluation model. The original KPI value and at least two original project indexes are training data required for training a KPI evaluation model, namely the original KPI value and at least two original project indexes are data contained in project information in historical projects, which is very helpful for training an accurate KPI evaluation model. The specific index contents of at least two current project indexes are consistent with the specific index contents of at least two original project indexes, and if the current project indexes are indexes such as human flow, display duration, geographical position, area, visibility, environmental interference degree, stay duration and the like, the original project indexes comprise the specific index contents corresponding to the current project indexes.
In this embodiment, original project information of the same project channel is acquired, and a data basis for performing subsequent KPI evaluation model training is provided based on an original KPI value and at least two original project indexes included in the original project information.
S22: and training by adopting a convolutional neural network model to obtain a KPI evaluation model based on the original KPI value and at least two original project indexes.
Among them, a Convolutional Neural Network (CNN) model is a feedforward Neural Network. Convolutional neural networks generally comprise at least two non-linearly trainable convolutional layers, at least two non-linear pooling layers and at least one fully-connected layer, i.e. comprising at least five hidden layers, in addition to an input layer and an output layer.
In this embodiment, the original KPI value and at least two original project indexes are trained by using the convolutional neural network model, so as to obtain the updated weights of each layer in the convolutional neural network model, obtain the KPI evaluation model based on the updated weights of each layer, and obtain the KPI evaluation model through training of the convolutional neural network model. The accuracy and the referential of the KPI values obtained by the KPI evaluation model are very high.
In a specific embodiment, as shown in fig. 5, in step S22, the training of the convolutional neural network model to obtain the KPI evaluation model based on the original KPI values and at least two original project indicators specifically includes the following steps:
s221: initializing the convolutional neural network model.
In this embodiment, initializing the convolutional neural network refers to initializing a convolutional kernel (i.e., a weight) and a bias of the convolutional layer, that is, assigning an initial value of the weight and the bias in the convolutional neural network model. If the initial weight is in a relatively flat area of the error surface, the convergence rate of the convolutional neural network model training may be abnormally slow. Typically, the weights of the network are initialized to be uniformly distributed in a relatively small interval with 0 mean, such as an interval of [ -0.10, +0.10 ].
S222: a feature map built from raw KPI values and at least two raw project indicators is input into a convolutional neural network model.
In this embodiment, a feature map created from raw KPI values and at least two raw project indicators is input into the convolutional neural network model. The original project index includes multiple dimensions, for example, the original project index of which the project channel is an outdoor advertisement may include dimensions of propagation extent, propagation depth, cost, effect evaluation, and the like. Each dimension can comprise a plurality of indexes, for example, the propagation breadth dimension can comprise original project indexes such as people flow and display duration. The original project indexes with different dimensions are normalized in advance, so that data with different dimensions and sources are unified under a reference system, the original project indexes with different dimensions can be compared and processed, a corresponding feature diagram (which essentially represents the relationship among the data with different dimensions) is established according to the original project indexes with different dimensions and the original KPI values of the project channel, namely, an original image is formed in a multi-dimensional space based on the original project indexes with different dimensions and the corresponding original KPI values, and then the original image is input into a convolutional neural network model to calculate the output of each layer.
S223: and calculating the output of each layer of the convolutional neural network model based on the characteristic diagram.
And calculating the output of each layer of the convolutional neural network model according to the characteristic diagram, wherein the output of each layer can be obtained by adopting a forward propagation algorithm. Different from a general fully-connected neural network model, for a locally-connected convolutional neural network model, a feature map of each output of a convolutional layer and a feature map of each output of a pooling layer in the model need to be calculated so as to update the weight. Specifically, a characteristic diagram x of each output of the convolutional layerjIs composed ofWhere l is the current layer, Mj represents the selected input feature map combination,is the output of the ith profile of the input i.e. the l-1 layer,is the convolution kernel used for the connection between the ith characteristic diagram of the I layer input and the jth characteristic diagram of the output,is additive bias corresponding to the j-th feature graph l layer, and f is an activation function, which can be a sigmoid activation function. Feature map x for each output of pooling layerjIs composed ofWherein down denotes down-sampling calculation, hereThe multiplicative bias corresponding to the l-th characteristic diagram layer of the j type, and b is the additive bias corresponding to the l-th characteristic diagram layer of the j type. In this embodiment, the convolution layer and pooling layer outputs different from the general fully-connected neural network model in the convolutional neural network model are mainly given, the outputs of the remaining layers are the same as the general fully-connected neural network model in calculation, and can be obtained by adopting a forward propagation algorithm, so that the above-mentioned calculation is not an example to avoid the need of redundancyThe above-mentioned processes are described.
S224: and performing error back-propagation updating on each layer of the convolutional neural network model according to the output of each layer of the convolutional neural network model to obtain the weight of each layer of the updated convolutional neural network model.
In step S223, errors inevitably exist between the outputs of the layers of the convolutional neural network model, and the error information needs to be returned to each layer by layer, so that each layer updates their weights, and the face recognition model with better recognition effect can be obtained. In this embodiment, performing error back-propagation update on each layer of the convolutional neural network model according to the output of each layer, and obtaining the updated weight of each layer, specifically including calculating error information of each layer of the convolutional neural network model, and updating the weight of each layer by using a gradient descent method. The weight updating by the gradient descent method mainly utilizes the gradient of the error cost function to the parameter, so the goal of weight updating is to make each layer obtain such gradient and then update.
In an embodiment, step S224 specifically includes the following steps: expression according to nth error cost functionSolving an nth error cost function, wherein E is the error cost function, n is a single training sample, and the output in the convolutional neural network model isThe actual output isc is the dimension of the actual output. To obtain the partial derivative of the error cost function to the parameter of a single sample, the sensitivity delta is defined as the rate of change of the error to the output, and the expression of the sensitivity isWhere E is an error cost function, where u is ul＝Wlxl-1+blAnd l denotes the current l-th layer, WlRepresents the weight, x, of the layerl-1Representing the input of the layer, blIndicating the additive bias of that layer. And the back propagation can be realized by calculating the layer-by-layer feedback error information of the sensitivity, wherein the back propagation process is a process of updating the error back propagation of each layer of the convolutional neural network model and acquiring the weight of each updated layer. The sensitivity of the first layer of the convolutional layer isWherein,for example, a downsampling operation with a signature size of 2, i.e., convolving the image with convolution kernels each having a value of 2 x 2 of 1/4, the weight W is actually the convolution kernel of 2 x 2, which has a value of βj. up represents the up-sampling calculation, which is a calculation opposite to the down-sampling calculation, and when the down-sampling calculation is performed, the sampling factor is n, and the up-sampling calculation is that each pixel is respectively copied by n times in the vertical direction and the horizontal direction. Since the sensitivity matrix of the l +1 pooling layer is 1/4 of the size of the sensitivity matrix of the l layer, upsampling calculation needs to be performed on the sensitivity matrix of the l +1 layer to make them consistent in size. Based on the obtained sensitivity, the partial derivative of the error cost function to the additive bias b is calculated asI.e., summing all nodes in sensitivity in layer l, where (u, v) represents the element position in the sensitivity matrix multiplicative bias β is related to the pooling layer of the current layer in forward propagation, thus defining firstThe partial derivative of the error cost function to the multiplicative bias β is calculated asThen calculating partial derivatives of the error cost function to the convolution kernel kHere, theIs thatWhen making convolution, with kijThe small block (u, v) in each feature map for convolution is the center of the small block, the value of the (u, v) position in the output feature map is formed by the small block of the (u, v) position in the input feature map and the convolution kernel kijThe resulting values are convolved. According to the operation of the formula, the weight of the convolution layer of the updated convolution neural network model can be obtained. In the training process of the convolutional neural network model, the pooling layer is also updated, and the feature map x of each output of the pooling layerjIs composed ofWhere down represents the down-sampling, where β is the multiplicative bias and b is the additive bias, the equation for the sensitivity of the pooling layer in the convolutional neural network model isAnd the partial derivative of the error cost function to the additive bias b can be obtained according to deltaWhere conv2, rot180 and full are functions required for calculation, the remaining parameters of the above formula are the same as those mentioned in the above convolutional layer formula, and will not be described in detail here. According to the formula, the updated pooling layer weight can be obtained; in addition, the weights among other layers (such as a fully-connected layer) of the convolutional neural network model are also updated, the updating process is the same as the weight updating method of the general fully-connected neural network model, and after the updating process is adopted, the weights are adoptedThe weights are updated to the propagation algorithm, and in order to avoid redundancy, the detailed description is not repeated. And (4) performing error back-propagation updating on each layer of the convolutional neural network model to obtain the updated weight of each layer.
S225: and acquiring the KPI evaluation model based on the updated weight values of all layers of the convolutional neural network model.
In this embodiment, the trained KPI evaluation model can be obtained by applying the obtained updated weights of each layer to the convolutional neural network model. Furthermore, the weight values between the KPI evaluation model layers reflect the potential relationship between the project indexes in different dimensions in the same project channel, and can reflect the influence of the project indexes in each dimension on the whole KPI evaluation, wherein the influence can be embodied as the weight values of different project indexes in each dimension. The method comprises the steps of establishing a corresponding feature diagram through an original KPI and original project indexes under a project channel corresponding to the original KPI, training the feature diagram by adopting a convolutional neural network model, obtaining weight values of all layers of the convolutional neural network model, wherein the weight values are reflected by the weight values of all the original project indexes occupying the original KPI, obtaining a KPI evaluation model with high evaluation accuracy according to the weight values, and the KPI evaluation model can help people to evaluate the current project indexes in a project acceptance process.
S30: and acquiring a current KPI value based on the KPI evaluation model and at least two current project indexes.
In this embodiment, according to an obtained KPI evaluation model corresponding to a project channel, at least two current project indexes are input in the KPI evaluation model, and the KPI evaluation model is adopted to process the input at least two current project indexes to obtain a current KPI value. The current KPI value is a result obtained by processing the current project index through a KPI evaluation model, and the potential relation between the project indexes with different dimensionalities can be better reflected through the KPI evaluation model trained by adopting the convolutional neural network model, so that the current KPI value with higher accuracy can be obtained based on the KPI evaluation model.
S40: and acquiring a target KPI value of the corresponding brand propaganda project based on the project ID.
In this embodiment, the target KPI value associated with the project ID is found in the database according to the project ID, and the target KPI calculation table is found according to the project ID to obtain the target KPI value, so that whether the brand promotion project meets the effect of the expected design is checked based on the obtained target KPI value. The target KPI value is preset, and the process of setting the target KPI value is described in step S13, and is not described herein again.
S50: and acquiring a project acceptance result of the brand propaganda project based on the current KPI value and the target KPI value.
In the embodiment, the current KPI value and the target KPI value are compared in size based on the current KPI value and the target KPI value; if the current KPI value is smaller than the target KPI value, the brand propaganda project can not reach the expected value set when the project is established; and if the current KPI value is greater than the target KPI value, the brand propaganda project can reach the target KPI value preset when establishing the project, and the completion condition of the brand project propaganda is considered to be in accordance with the expectation. The current KPI value is obtained according to a KPI evaluation model, the KPI evaluation model obtained by referring to historical data is closer to the actual situation, and the accuracy and the referenceability of the obtained current KPI value are high; the target KPI is a pre-designed 'pass line' of the brand advertising project, namely the target KPI is a judgment threshold value used for checking whether the current KPI reaches an expected value, and evaluating whether the completion condition of the brand advertising project meets the expectation.
In one embodiment, as shown in FIG. 6, the brand advertising item management method further includes the steps of:
s61: and acquiring a supplier information recommendation instruction, wherein the supplier information recommendation instruction comprises at least one classification index and a sorting mode.
Specifically, the item acceptance information further includes vendor information corresponding to the item ID. The provider information recommendation instruction is an instruction for making a provider information recommendation. The supplier information recommendation instruction comprises at least one classification index and a sorting mode. The classification index is a classification standard for distinguishing supplier information, and the classification index includes item size, item amount and other classification indexes, for example, the classification indexes are classified according to the amount of items of 0-50 ten thousand, 51-100 ten thousand, 101-500 ten thousand and more than 501 ten thousand. The sorting manner refers to a sorting method for sorting the provider information, such as an ascending order, a sorting order, and the like.
In this embodiment, the terminal device obtains a supplier information recommendation instruction input by a user, where the supplier information recommendation instruction includes at least one classification index and a sorting mode, and is used to distinguish and sort items, and obtain supplier information recommendation information required by the user.
S62: and acquiring a corresponding supplier information table according to at least one classification index.
In this embodiment, the terminal device finds the provider information table stored in the database and corresponding to the classification index according to the classification index included in the obtained provider information recommendation instruction. The supplier information table is a table which is created in the database in advance according to all classification indexes, and a user can directly acquire the corresponding supplier information table stored in the database according to the classification indexes.
S63: and sequencing the current KPI values in the supplier information table according to the sequencing mode to obtain a supplier recommendation list.
In this embodiment, the terminal device sorts the current KPI values in the provider information table according to the sorting manner included in the obtained provider information recommendation instruction, so as to obtain a sorted provider recommendation list, so that a suitable provider is selected for cooperation based on the sorted provider recommendation list, and the probability of achieving an expected follow-up brand promotion item is improved.
According to the brand propaganda project management method provided by the embodiment, project acceptance information is obtained firstly, the project acceptance information comprises a project ID, a project channel and at least two current project indexes, a data basis for brand propaganda project management is effectively provided by obtaining the project acceptance information, and help is provided for obtaining a KPI evaluation model and a current KPI value subsequently. And then acquiring a corresponding KPI evaluation model based on the project channel, acquiring the corresponding KPI evaluation model according to the project channel through the project channel, and providing an evaluation model suitable for the project channel corresponding to the current KPI for acquiring the current KPI. And then, acquiring a current KPI value based on the KPI evaluation model and at least two current project indexes, and acquiring the current KPI value by using the KPI evaluation model and the current project indexes, thereby providing an important data basis for subsequently acquiring a project acceptance result. And then, based on the project ID, acquiring a target KPI value of the corresponding brand propaganda project, and by acquiring the target KPI value of the corresponding brand propaganda project, the effect of checking whether the brand propaganda project conforms to the expected design on the current KPI value is favorably realized through the target KPI value. And finally, acquiring a project acceptance result of the brand propaganda project based on the current KPI value and the target KPI value, and evaluating the completion condition of the brand propaganda project by comparing the current KPI value with the target KPI value to determine whether the brand propaganda project reaches an expected value, namely, visually evaluating the completion effect of the brand propaganda project by adopting the calculated current KPI value.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Example 2
Fig. 7 is a schematic block diagram of a brand promotion item management apparatus corresponding to the brand promotion item management method according to embodiment 1. As shown in fig. 7, the brand promotion project management apparatus includes a project acceptance information acquisition module 10, a KPI evaluation model acquisition module 20, a current KPI value acquisition module 30, a target KPI value acquisition module 40, and a project acceptance result acquisition module 50. The implementation functions of the project acceptance information obtaining module 10, the KPI evaluation model obtaining module 20, the current KPI value obtaining module 30, the target KPI value obtaining module 40, and the project acceptance result obtaining module 50 correspond to the steps corresponding to the brand promotion project management method in the embodiment one by one, and in order to avoid redundancy, detailed description is not provided in this embodiment.
The project acceptance information acquiring module 10 is configured to acquire project acceptance information, where the project acceptance information includes a project ID, a project channel, and at least two current project indexes.
And the KPI evaluation model obtaining module 20 is configured to obtain a corresponding KPI evaluation model based on a project channel.
And a current KPI value obtaining module 30, configured to obtain a current KPI value based on the KPI evaluation model and at least two current project indicators.
And the target KPI value acquisition module 40 is configured to acquire a target KPI value of a corresponding brand promotion project based on the project ID.
And the project acceptance result acquisition module 50 is used for acquiring a project acceptance result of the brand propaganda project based on the current KPI value and the target KPI value.
The brand promotion management apparatus further includes a KPI evaluation model training module 60 and a supplier recommendation list acquisition module 70.
And a KPI evaluation model training module 60, configured to train the KPI evaluation model in advance.
A supplier recommendation list obtaining module 70, configured to obtain a supplier recommendation list.
Preferably, the KPI evaluation model training module 60 includes an original project information obtaining unit 61 and a KPI evaluation model obtaining unit 62.
Preferably, the KPI evaluation model obtaining unit 62 includes an initialization sub-unit 621, a feature map establishing sub-unit 622, a layer output obtaining sub-unit 623, a weight updating sub-unit 624, and a KPI evaluation model sub-unit 625.
An initialization subunit 621 configured to initialize the convolutional neural network model.
The feature map creation subunit 622 is configured to input a feature map created by the raw KPI values and at least two raw project indicators in the convolutional neural network model.
And the layer output acquisition subunit 623 is configured to calculate outputs of each layer of the convolutional neural network model based on the feature map.
And a weight updating subunit 624, configured to perform error back-propagation updating on each layer of the convolutional neural network model according to the output of each layer of the convolutional neural network model, and obtain weights of each layer of the updated convolutional neural network model.
And a KPI evaluation model subunit 625, configured to obtain a KPI evaluation model based on the updated weights of each layer of the convolutional neural network model.
Preferably, the provider recommendation list acquisition module 70 includes a recommendation instruction acquisition unit 71, a provider information table acquisition unit 72, and a provider recommendation list acquisition unit 73.
The recommendation instruction obtaining unit 71 is configured to obtain a provider information recommendation instruction, where the provider information recommendation instruction includes at least one classification index and a sorting manner.
A supplier information table obtaining unit 72, configured to obtain a corresponding supplier information table according to at least one classification index.
The provider recommendation list obtaining unit 73 is configured to sort the current KPI values in the provider information table according to the sorting manner, and obtain a provider recommendation list.
The brand promotion item management apparatus further includes an item establishment information acquisition unit 81, a KPI calculation table acquisition unit 82, and a target KPI value calculation unit 83.
Preferably, the project standing item information acquiring unit 81 includes a project expense application information acquiring unit 811 and a project expense information table determining unit 812.
The project expense application information acquiring subunit 811 is configured to acquire project expense application information, where the project expense application information includes a current expense subject and a specific expense value.
A project expense information table determining subunit 812, configured to determine a project expense information table based on the current expense subject and the specific expense value if the current expense subject is the standard expense subject;
and if the current expense subject is not the standard expense subject, converting the current expense subject by adopting a preset project subject conversion table to obtain the corresponding standard expense subject, and determining a project expense information table based on the standard expense subject and the specific expense value.
In the brand propaganda project management device provided by this embodiment, the project acceptance information obtaining module 10 is configured to obtain project acceptance information, where the project acceptance information includes a project ID, a project channel, and at least two current project indexes, and by obtaining the project acceptance information, a data basis for performing brand propaganda project management is effectively provided, and help is provided for subsequently obtaining a KPI evaluation model and a current KPI value. And a KPI evaluation model obtaining module 20, configured to obtain a corresponding KPI evaluation model based on a project channel, obtain the corresponding KPI evaluation model according to the project channel through the project channel, and provide an evaluation model suitable for the project channel corresponding to the current KPI for obtaining the current KPI. And the current KPI value obtaining module 30 is configured to obtain a current KPI value based on the KPI evaluation model and at least two current project indexes, and obtain the current KPI value by using the KPI evaluation model and the current project indexes, so as to provide an important data basis for subsequently obtaining a project acceptance result. And the target KPI value acquisition module 40 is configured to acquire a target KPI value of the corresponding brand advertising project based on the project ID, and is beneficial to achieving an effect of checking whether the brand advertising project conforms to an expected design on the current KPI value through the target KPI value. And the project acceptance result acquisition module 50 is configured to acquire a project acceptance result of the brand advertising project based on the current KPI value and the target KPI value, and evaluate the completion condition of the brand advertising project by comparing the current KPI value with the target KPI value to determine whether the brand advertising project reaches an expected value, so that the brand advertising project can be visually evaluated by using the calculated current KPI value.
Example 3
This embodiment provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method for managing the brand publicity items in embodiment 1 is implemented, and in order to avoid redundancy, details are not described here. Alternatively, the computer program, when executed by the processor, implements the functions of each module/unit in the brand promotion item management apparatus in embodiment 2, and is not described herein again to avoid redundancy.
Example 4
Fig. 8 is a schematic diagram of the terminal device in the present embodiment. As shown in fig. 8, the terminal device 90 includes a processor 91, a memory 92, and a computer program 93 stored in the memory 92 and executable on the processor 91. The processor 91, when executing the computer program 93, implements the respective steps of the card promotion item management method in embodiment 1, such as steps S10, S20, S30, S40, and S50 shown in fig. 1. Alternatively, the processor 91 executes the computer program 93 to realize the functions of the respective modules/units of the brand promotion project management apparatus in embodiment 2, such as the functions of the project acceptance information acquisition module 10, the KPI evaluation model acquisition module 20, the current KPI value acquisition module 30, the target KPI value acquisition module 40, and the project acceptance result acquisition module 50 shown in fig. 7.
Illustratively, the computer program 93 may be divided into one or more modules/units, which are stored in the memory 92 and executed by the processor 91 to implement the present invention. One or more of the modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 93 in the terminal device 90. For example, the computer program 90 may be divided into the project acceptance information obtaining module 10, the KPI evaluation model obtaining module 20, the current KPI value obtaining module 30, the target KPI value obtaining module 40, and the project acceptance result obtaining module 50 in embodiment 2, and specific functions of each module are as shown in embodiment 2, which are not repeated herein.
The terminal device 90 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal device may include, but is not limited to, a processor 91, a memory 92. Those skilled in the art will appreciate that fig. 8 is merely an example of a terminal device 90 and does not constitute a limitation of the terminal device 90 and may include more or fewer components than shown, or some components may be combined, or different components, e.g., the terminal device may also include input output devices, network access devices, buses, etc.
The Processor 91 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 92 may be an internal storage unit of the terminal device 90, such as a hard disk or a memory of the terminal device 90. The memory 92 may also be an external storage device of the terminal device 90, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like provided on the terminal device 90. Further, the memory 92 may also include both an internal storage unit of the terminal device 90 and an external storage device. The memory 92 is used to store computer programs and other programs and data required by the terminal device. The memory 92 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media which may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A method for brand promotional item management, comprising:
acquiring project acceptance information, wherein the project acceptance information comprises a project ID, a project channel and at least two current project indexes;
acquiring a corresponding KPI (Key performance indicator) evaluation model based on the project channel;
acquiring a current KPI value based on the KPI evaluation model and at least two current project indexes;
acquiring a target KPI value of a corresponding brand propaganda project based on the project ID;
and acquiring a project acceptance result of the brand propaganda project based on the current KPI value and the target KPI value.
2. The brand advertising project management method of claim 1, wherein prior to the step of obtaining a corresponding KPI evaluation model based on the project channel, the brand advertising project management method further comprises: pre-training the KPI evaluation model;
the step of pre-training the KPI assessment model comprises:
acquiring original project information of the same project channel, wherein the original project information comprises an original KPI value and at least two original project indexes;
and training by adopting a convolutional neural network model to obtain the KPI evaluation model based on the original KPI value and at least two original project indexes.
3. The method for managing brand publicity project of claim 2, wherein the training of the convolutional neural network model to obtain the KPI evaluation model based on the original KPI value and at least two of the original project indicators comprises:
initializing the convolutional neural network model;
inputting a feature map built by the original KPI values and at least two of the original project indicators in the convolutional neural network model;
calculating the output of each layer of the convolutional neural network model based on the characteristic diagram; wherein each output characteristic diagram x of the convolution layerjIs composed ofWhere l is the current layer, Mj represents the selected input feature map combination,is the ith kind of feature map of the input,is the convolution kernel used for the connection between the ith characteristic diagram of the I layer input and the jth characteristic diagram of the output,is the additive bias corresponding to the l layer of the j-th feature graph, and f is the activation function; feature map x for each output of pooling layerjIs composed ofWherein down denotes down-sampling calculation, hereThe multiplicative bias corresponding to the l-th characteristic diagram layer,is the additive bias corresponding to the l layer of the j-th feature map;
performing error back-propagation updating on each layer of the convolutional neural network model according to the output of each layer of the convolutional neural network model to obtain the weight of each layer of the convolutional neural network model after updating;
and acquiring a KPI evaluation model based on the updated weight values of all layers of the convolutional neural network model.
4. The brand advertising item management method according to claim 1, wherein the item acceptance information further includes vendor information corresponding to the item ID;
after the step of obtaining a current KPI value based on the KPI evaluation model and at least two of the current project indicators, the brand advertising project management method further comprises:
obtaining a supplier information recommendation instruction, wherein the supplier information recommendation instruction comprises at least one classification index and a sorting mode;
acquiring a corresponding supplier information table according to at least one classification index;
and sequencing the current KPI values in the supplier information table according to the sequencing mode to obtain a supplier recommendation list.
5. The method for managing a brand advertising project according to claim 1, wherein the acquiring of the project acceptance information further comprises:
acquiring project establishment information, wherein the project establishment information comprises a project ID, a project type, a project channel and project budget expenditure;
acquiring a project expense range and a target KPI calculation table based on the project type and the project channel;
and if the project budget expenditure is in the project expenditure range, acquiring a target KPI value corresponding to the project ID through the application of project item establishment information and based on the target KPI calculation table and the project budget expenditure.
6. The brand advertising item management method according to claim 5, wherein the item standing information further includes an item expense information table;
the acquiring project establishment information comprises:
acquiring project expense application information, wherein the project expense application information comprises a current expense subject and a specific expense value;
if the current expense subject is a standard expense subject, determining the project expense information table based on the current expense subject and the specific expense value;
if the current expense subject is not the standard expense subject, converting the current expense subject by adopting a preset project subject conversion table, taking the corresponding standard expense subject, and determining the project expense information table based on the standard expense subject and the specific expense value.
7. A brand promotion item management apparatus, comprising:
the project acceptance information acquisition module is used for acquiring project acceptance information, and the project acceptance information comprises a project ID, a project channel and at least two current project indexes;
the KPI evaluation model acquisition module is used for acquiring a corresponding KPI evaluation model based on the project channel;
a current KPI value obtaining module, configured to obtain a current KPI value based on the KPI evaluation model and at least two current project indicators;
the target KPI value acquisition module is used for acquiring a target KPI value of a corresponding brand propaganda project based on the project ID;
and the project acceptance result acquisition module is used for acquiring a project acceptance result of the brand propaganda project based on the current KPI value and the target KPI value.
8. The brand advertising project management apparatus of claim 7, further comprising a KPI evaluation model training module; the KPI evaluation model training module comprises:
the system comprises an original project information acquisition unit, a data processing unit and a data processing unit, wherein the original project information acquisition unit is used for acquiring original project information of the same project channel, and the original project information comprises an original KPI value and at least two original project indexes;
and the KPI evaluation model obtaining unit is used for training the original KPI value and at least two original project indexes by adopting a convolutional neural network model to obtain the KPI evaluation model.
9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the brand promotion item management method of any one of claims 1 to 6.
10. A computer-readable medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the brand advertising program management method as claimed in any one of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711429863.0A CN108229804A (en) | 2017-12-26 | 2017-12-26 | Brand promotion project management method, device, terminal device and storage medium |
| PCT/CN2018/074661 WO2019127822A1 (en) | 2017-12-26 | 2018-01-31 | Brand promotion project management method and apparatus, terminal device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711429863.0A CN108229804A (en) | 2017-12-26 | 2017-12-26 | Brand promotion project management method, device, terminal device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108229804A true CN108229804A (en) | 2018-06-29 |
Family
ID=62647959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711429863.0A Pending CN108229804A (en) | 2017-12-26 | 2017-12-26 | Brand promotion project management method, device, terminal device and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108229804A (en) |
| WO (1) | WO2019127822A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109002997A (en) * | 2018-07-26 | 2018-12-14 | 郑州云海信息技术有限公司 | Accounting method and system based on SV server product line working hour KPI under MES data |
| CN110045798A (en) * | 2019-04-25 | 2019-07-23 | 烟台工程职业技术学院(烟台市技师学院) | A kind of brand promotion project management terminal device |
| US11741364B2 (en) * | 2018-04-10 | 2023-08-29 | Hookit, Llc | Deep neural networks modeling |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521706A (en) * | 2011-12-16 | 2012-06-27 | 北京斯泰威网络科技有限公司 | KPI data analysis method and device for the same |
| CN104616107A (en) * | 2015-02-03 | 2015-05-13 | 北方信息控制集团有限公司 | Scientific research performance KPI management method and management system |
-
2017
- 2017-12-26 CN CN201711429863.0A patent/CN108229804A/en active Pending
-
2018
- 2018-01-31 WO PCT/CN2018/074661 patent/WO2019127822A1/en active Application Filing
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11741364B2 (en) * | 2018-04-10 | 2023-08-29 | Hookit, Llc | Deep neural networks modeling |
| CN109002997A (en) * | 2018-07-26 | 2018-12-14 | 郑州云海信息技术有限公司 | Accounting method and system based on SV server product line working hour KPI under MES data |
| CN109002997B (en) * | 2018-07-26 | 2021-11-26 | 郑州云海信息技术有限公司 | SV server product line working hour KPI accounting method and system based on MES data |
| CN110045798A (en) * | 2019-04-25 | 2019-07-23 | 烟台工程职业技术学院(烟台市技师学院) | A kind of brand promotion project management terminal device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019127822A1 (en) | 2019-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11544793B2 (en) | Dimensionality reduction of multi-attribute consumer profiles | |
| US11532052B2 (en) | Using simulated consumer profiles to form calibration data for models | |
| CN108564286B (en) | Artificial intelligent financial wind-control credit assessment method and system based on big data credit investigation | |
| US20180336640A1 (en) | Rate analyzer models and user interfaces | |
| US9418337B1 (en) | Systems and models for data analytics | |
| CN108876166A (en) | Financial risk authentication processing method, device, computer equipment and storage medium | |
| CN108197652B (en) | Method and apparatus for generating information | |
| CN113159147A (en) | Image identification method and device based on neural network and electronic equipment | |
| CN112148973B (en) | Data processing method and device for information push | |
| Dittrich et al. | Network autocorrelation modeling: A Bayes factor approach for testing (multiple) precise and interval hypotheses | |
| CN108229804A (en) | Brand promotion project management method, device, terminal device and storage medium | |
| CN110852785B (en) | User grading method, device and computer readable storage medium | |
| CN108921398A (en) | Shop quality evaluating method and device | |
| CN111639690A (en) | Fraud analysis method, system, medium, and apparatus based on relational graph learning | |
| Dreassi et al. | Small area estimation for semicontinuous skewed spatial data: An application to the grape wine production in Tuscany | |
| CN106708729A (en) | Code defect predicting method and device | |
| CN115271976A (en) | Advisory recommendation method and device and computer readable storage medium | |
| CN113407854A (en) | Application recommendation method, device and equipment and computer readable storage medium | |
| CN112150184A (en) | Click rate estimation method and system, computer system and computer readable medium | |
| US20230325632A1 (en) | Automated anomaly detection using a hybrid machine learning system | |
| CN112084825B (en) | Cooking evaluation method, cooking recommendation method, computer device and storage medium | |
| CN117522519A (en) | Product recommendation method, device, apparatus, storage medium and program product | |
| US20110231336A1 (en) | Forecasting product/service realization profiles | |
| CN114169938A (en) | Information pushing method, device, equipment and storage medium | |
| CN109598410A (en) | Presell methods of risk assessment, system, computer installation and readable storage medium storing program for executing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180629 |
|
| RJ01 | Rejection of invention patent application after publication |