WO2020087828A1 - 预售风险评估方法、系统、计算机装置及可读存储介质 - Google Patents

预售风险评估方法、系统、计算机装置及可读存储介质 Download PDF

Info

Publication number
WO2020087828A1
WO2020087828A1 PCT/CN2019/077514 CN2019077514W WO2020087828A1 WO 2020087828 A1 WO2020087828 A1 WO 2020087828A1 CN 2019077514 W CN2019077514 W CN 2019077514W WO 2020087828 A1 WO2020087828 A1 WO 2020087828A1
Authority
WO
WIPO (PCT)
Prior art keywords
sale
information
risk assessment
evaluation value
merchant
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.)
Ceased
Application number
PCT/CN2019/077514
Other languages
English (en)
French (fr)
Inventor
甘文俊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2020087828A1 publication Critical patent/WO2020087828A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q10/0635—Risk analysis of enterprise or organisation activities

Definitions

  • the present application relates to the field of data processing, and in particular, to a pre-sale risk assessment method, system, computer device, and readable storage medium.
  • Pre-sale refers to the sales behavior before the product has officially entered the market. You can use pre-sale to know whether there is a market for this product, especially for some products that can only be produced in batches. It was put into production after the amount was measured, effectively avoiding the risks in production. Now merchants like to do pre-sale marketing activities before the sale of goods to attract customers. No matter what kind of product the merchant has, there are certain risks in its operation. Once the merchant does not manage well, or the merchant deliberately scams, it is easy to cause economic losses to the user.
  • the present application provides a pre-sale risk assessment method, system, computer device, and storage medium, which can implement risk prediction for merchant pre-sale behavior.
  • An embodiment of the present application provides a pre-sale risk assessment method.
  • the method includes:
  • the historical feature data is data that a merchant has initiated a pre-sale behavior and has a pre-sale result, and the pre-sale result includes a pre-sale success and a pre-sale failure;
  • Input historical feature data corresponding to different pre-sale results to the neural network model for training to obtain the first risk assessment model corresponding to the success of the pre-sale and the second risk assessment model corresponding to the failure of the pre-sale;
  • the success rate of the pre-sale activity to be calculated is calculated according to the first evaluation value and the second evaluation value.
  • An embodiment of the present application provides a pre-sale risk assessment system.
  • the system includes:
  • the first acquisition module is used for historical feature data, wherein the historical feature data is data that a merchant has initiated a pre-sale behavior and has a pre-sale result, and the pre-sale result includes a pre-sale success and a pre-sale failure;
  • the model training module is used to input the historical feature data corresponding to different pre-sale results to the neural network model for training, respectively, to obtain the first risk assessment model corresponding to the pre-sale success and the second corresponding to the pre-sale failure Risk assessment model;
  • a second obtaining module configured to obtain characteristic data of a pre-sale activity to be entered, and input the characteristic data into the first risk assessment model to obtain a first evaluation value, and input the characteristic data into the first
  • the second risk assessment model obtains the second assessment value
  • the calculation module is configured to calculate the success rate of the pre-sale activity to be performed according to the first evaluation value and the second evaluation value.
  • An embodiment of the present application provides a computer device.
  • the computer device includes a processor and a memory.
  • the memory stores a plurality of computer-readable instructions.
  • the processor is used to execute the computer-readable instructions stored in the memory. The steps of the pre-sale risk assessment method described above.
  • An embodiment of the present application provides a non-volatile readable storage medium on which computer-readable instructions are stored.
  • the steps of the pre-sale risk assessment method described above are implemented .
  • the above pre-sale risk assessment method, system, computer device, and non-volatile readable storage medium are based on machine learning and historical merchant pre-sale data to establish and train a risk assessment model, and incorporate the characteristics of the merchant to be pre-sold.
  • the data is input into the risk assessment model to calculate the success rate of the merchant's pre-sale activities, and then the user can determine whether to participate in the merchant's pre-sale activities according to the success rate, to avoid economic losses.
  • FIG. 1 is a flowchart of steps of a pre-sale risk assessment method in an embodiment of the present application.
  • FIG. 2 is a flowchart of steps of a pre-sale risk assessment method in another embodiment of the present application.
  • FIG. 3 is a functional block diagram of a pre-sale risk assessment system in an embodiment of the application.
  • FIG. 4 is a schematic diagram of a computer device in an embodiment of the application.
  • the pre-sale risk assessment method of the present application is applied to one or more computer devices.
  • the computer device is a device that can automatically perform numerical calculation and / or information processing according to a preset or stored instruction, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) , Programmable gate array (Field-Programmable Gate Array, FPGA), digital processor (Digital Signal Processor, DSP), embedded equipment, etc.
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • DSP Digital Signal Processor
  • the computer device may be a computing device such as a desktop computer, a notebook computer, a tablet computer, and a server.
  • the computer device can interact with the user through a keyboard, a mouse, a remote control, a touchpad, or a voice control device.
  • FIG. 1 is a flowchart of steps of a preferred embodiment of the pre-sale risk assessment method of this application. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.
  • the pre-sale risk assessment method specifically includes the following steps.
  • Step S11 Obtain historical feature data, where the historical feature data is data that a merchant has initiated a pre-sale behavior and has a pre-sale result, and the pre-sale result includes a pre-sale success and a pre-sale failure.
  • a merchant data sample database can be connected to the network to obtain historical feature data related to merchant pre-sales.
  • the merchant data sample database may collect historical feature data of multiple merchants who have conducted pre-sale activities through big data, or may enter historical feature data related to merchant pre-sales entered manually by the recipient.
  • historical feature data related to merchant pre-sale includes but is not limited to multiple merchant dimension information
  • the multiple merchant dimension information includes but is not limited to: merchant registered capital information, number of shareholders information, shareholder credit record information , Information about the city where the store is located, information about the location of the store, information about the industry to which the merchant belongs, information about the strength of the merchandise, information about the time of the merchandise, information about the cost of the product, information about the time of opening, information about the profit or loss of the merchant, and information about the number of customers.
  • a pre-processing operation may be performed on the acquired feature data. Understandably, there may be one or more merchant dimension information with missing data information in the historical feature data.
  • the merchant dimension information corresponding to the missing data information may be set as a preset default value. For example, if the merchant dimension information is merchandise discount strength information, if the historical feature data of a merchant does not have merchandise discount strength information, it means that the merchant has no discount when conducting pre-sale activities. At this time, the merchant ’s merchandise discount strength can be The information is set to a preset default value (assuming the preset default value is 0).
  • the historical feature data related to the merchant's pre-sale can be obtained from the structured merchant data sample database, and the historical feature data obtained at this time can be directly subjected to subsequent processing.
  • historical feature data related to merchant pre-sales may also be unstructured data, such as data stored in text. Therefore, when pre-processing the historical feature data, corresponding feature data can also be obtained from the unstructured data.
  • the multiple merchant dimension information includes: merchant registered capital information, number of shareholders information, Shareholder credit record information, store location city information, store location information, merchant's industry information, product preferential strength information, preferential time information, product cost information, opening time information; then the keywords corresponding to these merchant dimension information are: registration Capital, number of shareholders, shareholder credit history, city, location, industry, preferential strength, preferential time, cost, opening time.
  • the unstructured data contains "Preferential time is January 1, 2017", because it contains the keyword "Preferential time”, the corresponding feature data can be obtained according to the keyword "Preferential time” is "2017 1 January 1. "
  • Step S12 Input historical feature data corresponding to different pre-sale results to the neural network model for training to obtain the first risk assessment model corresponding to the success of the pre-sale and the second risk assessment model corresponding to the failure of the pre-sale .
  • the historical feature data can be classified according to the pre-sale results as pre-sale success and pre-sale failure, using the pre-sale success historical feature data as the first sample data set, and pre-sale failure historical features The data is used as the second sample data set.
  • the first risk assessment model and the second risk assessment model may be models trained based on the neural network model and the first sample data set and the second sample data set.
  • the neural network model can abstract the human brain neuron network from the perspective of information processing, and form different networks according to different connection methods. There is no need to determine the mathematical equation of the mapping relationship between input and output in advance. Only through its own training, in When the input value is given, the result closest to the expected output value is obtained.
  • the neural network model includes an input layer, a hidden layer, and an output layer. The historical feature data can be used as the input layer of the neural network model, and then through the connection of the hidden layer of the neural network model, an evaluation value is output from the output layer.
  • the historical feature data of the pre-sale result being the pre-sale success may be input to the first neural network model for training to obtain the first risk An evaluation model, inputting the historical feature data of the pre-sale failure as the pre-sale failure into the second neural network model for training, to obtain the second risk evaluation model.
  • the neural network model may be a BP (Back Propagation, Back Propagation) neural network model.
  • the BP neural network model is a multi-layer feed-forward network based on the gradient descent method and trained by error back propagation, using a gradient search Technology to minimize the mean square error of the actual output value and expected output value of the network.
  • other types of neural network models may also be selected according to actual needs.
  • the input layer includes n nodes
  • the hidden layer includes m nodes
  • the BP neural network model may be expressed as:
  • y is the output value of the output layer
  • the output value y of the first risk assessment model is the first assessment value
  • the output value y of the second risk assessment model is the second assessment value
  • S i is the input of the hidden layer, that is, the output of the input layer
  • W ij is the The connection weight between the input layer and the hidden layer
  • f ( ⁇ ) is the activation function in the BP neural network model, and when the hidden layer has an input, the activation function is expressed as f (S i ).
  • the activation function f (S i ) can use an S-type function (Sigmoid function), and f (S i ) can be expressed as:
  • t i may represent the connection weight between the i-th node of the hidden layer and the output layer, for example, t 1 is the first node of the hidden layer and the output layer
  • the connection weight between t 2 is the connection weight between the second node of the hidden layer and the output layer
  • t 3 is the third node of the hidden layer and the output layer connection weight between
  • t m is the weight of the connection node between the m-th hidden layer and the output layer weights.
  • W ij is the connection weight between the i-th node of the hidden layer and the j-th node of the input layer.
  • Step S13 Obtain characteristic data of a pre-sale activity to be entered, and input the characteristic data into the first risk evaluation model to obtain a first evaluation value, and input the characteristic data into the second risk evaluation model The second evaluation value is obtained.
  • a merchant A when a merchant A prepares to carry out a pre-sale activity, it can obtain the characteristic data of the merchant A.
  • the characteristic data of the merchant A includes merchant registered capital information, number of shareholders information, shareholder credit record information, store city Information, store location information, merchant's industry information, product discount strength information, discount time information, product cost information, opening time information, merchant profit or loss information, customer number information.
  • the first risk assessment model is constructed based on the historical feature data of the pre-sale success. Therefore, the feature data of the merchant A is input to the first risk assessment model to obtain a first assessment value, the first assessment value It can be used to predict the probability of successful pre-sale of merchant A.
  • the second risk assessment model is constructed based on historical feature data of pre-sale failure. Therefore, the feature data of merchant A is input to the second risk assessment model to obtain a second assessment value, and the second assessment value It can be used to predict the probability of failure of the pre-sale of merchant A.
  • Step S14 Calculate the success rate of the pre-sale activity based on the first evaluation value and the second evaluation value.
  • a first weight coefficient and a second weight coefficient may be set in advance for the first evaluation value and the second evaluation value, respectively, where the first evaluation value corresponds to the first weight coefficient, the first The second evaluation value corresponds to the second weight coefficient, and then the product of the first evaluation value and the first weight coefficient is subtracted from the product of the second evaluation value and the second weight coefficient to obtain the merchant A to be performed
  • the pre-sale risk assessment method shown in FIG. 2 further includes steps S15, S16 and S17.
  • Step S15 Determine whether the success rate of the pre-sale activity to be performed is greater than a preset threshold
  • Step S16 When the success rate of the pre-sale activity to be performed is greater than the preset threshold, output first prompt information
  • Step S17 When the success rate of the pre-sale activity to be performed is not greater than the preset threshold, output second prompt information.
  • the success rate of the pre-sale activity to be performed is greater than the preset threshold, it indicates that the merchant A ’s pre-sale success probability is greater than the failure probability, the merchant ’s business risk is low, and the user can participate in the merchant A ’s
  • the success rate of the pre-sale activity to be carried out is not greater than the preset threshold, it indicates that the merchant A ’s pre-sale success rate is less than the failure probability, and the merchant ’s business risk is high. It is not recommended that users participate in the merchant ’s business.
  • the preset threshold can be set and adjusted according to actual usage requirements. For example, the preset threshold is set to 0.5.
  • the first prompt message may be: the risk of pre-sale is low, you can choose to participate in the pre-sale activity of merchant A; if the pre-sale of merchant A is calculated successfully If the rate is not greater than 0.5, it means that the merchant A ’s pre-sale success probability is less than the failure probability, and a second prompt message is output to the user.
  • the second prompt message may be: the pre-sale risk is higher, and it is not recommended to participate in the merchant A ’s Pre-sale activities.
  • FIG. 3 is a functional block diagram of a preferred embodiment of the pre-sale risk assessment system of the application.
  • the pre-sale risk assessment system 10 may include a first acquisition module 101, a model training module 102, a second acquisition module 103, a calculation module 104, and an output module 105.
  • the acquisition module 101 is used for historical feature data, where the historical feature data is data that a merchant has initiated a pre-sale behavior and has a pre-sale result, and the pre-sale result includes a pre-sale success and a pre-sale failure.
  • the acquiring module 101 may connect to a merchant data sample database by accessing a network, and then acquire historical feature data related to merchant pre-sales.
  • the merchant data sample database may collect historical feature data of multiple merchants who have conducted pre-sale activities through big data, or may enter historical feature data related to merchant pre-sales entered manually by the recipient.
  • historical feature data related to merchant pre-sale includes but is not limited to multiple merchant dimension information
  • the multiple merchant dimension information includes but is not limited to: merchant registered capital information, number of shareholders information, shareholder credit record information , Information about the city where the store is located, information about the location of the store, information about the industry to which the merchant belongs, information about the strength of the merchandise, information about the time of the merchandise, information about the cost of the product, information about the time of opening, information about the profit or loss of the merchant, and information about the number of customers.
  • the acquiring module 101 may also perform a preprocessing operation on the acquired feature data. Understandably, there may be one or more merchant dimension information with missing data information in the historical feature data.
  • the merchant dimension information corresponding to the missing data information may be set as a preset default value. For example, if the merchant dimension information is merchandise discount strength information, if the historical feature data of a merchant does not have merchandise discount strength information, it means that the merchant has no discount when conducting pre-sale activities. At this time, the merchant ’s merchandise discount strength can be The information is set to a preset default value (assuming the preset default value is 0).
  • the historical feature data related to the merchant's pre-sale can be obtained from the structured merchant data sample database, and the historical feature data obtained at this time can be directly subjected to subsequent processing.
  • historical feature data related to merchant pre-sales may also be unstructured data, such as data stored in text. Therefore, when pre-processing the historical feature data, corresponding feature data can also be obtained from the unstructured data.
  • the multiple merchant dimension information includes: merchant registered capital information, number of shareholders information, Shareholder credit record information, store location city information, store location information, merchant's industry information, product preferential strength information, preferential time information, product cost information, opening time information; then the keywords corresponding to these merchant dimension information are: registration Capital, number of shareholders, shareholder credit history, city, location, industry, preferential strength, preferential time, cost, opening time.
  • the unstructured data contains "Preferential time is January 1, 2017", because it contains the keyword "Preferential time”, the corresponding feature data can be obtained according to the keyword "Preferential time” is "2017 1 January 1. "
  • the model training module 102 is used to input historical feature data corresponding to different pre-sale results to the neural network model for training, respectively, to obtain the first risk assessment model corresponding to the pre-sale success and the corresponding to the pre-sale failure The second risk assessment model.
  • the historical feature data may be classified according to the pre-sale results as pre-sale success and pre-sale failure, using the pre-sale success historical feature data as the first sample data set, and pre-sale failure history The feature data is used as the second sample data set.
  • the first risk assessment model and the second risk assessment model may be models trained based on the neural network model and the first sample data set and the second sample data set.
  • the neural network model can abstract the human brain neuron network from the perspective of information processing, and form different networks according to different connection methods. There is no need to determine the mathematical equation of the mapping relationship between input and output in advance. When the input value is given, the result closest to the expected output value is obtained.
  • the neural network model includes an input layer, a hidden layer, and an output layer. The historical feature data can be used as the input layer of the neural network model, and then through the connection of the hidden layer of the neural network model, an evaluation value is output from the output layer.
  • the model training module 102 may input the historical feature data of the pre-sale result as the pre-sale success to the first neural network model for training, Obtain the first risk assessment model, input the historical feature data of the pre-sale failure as the pre-sale failure into the second neural network model for training, and obtain the second risk assessment model.
  • the neural network model may be a BP (Back Propagation, Back Propagation) neural network model.
  • the BP neural network model is a multi-layer feed-forward network based on the gradient descent method and trained by error back propagation, using a gradient search Technology to minimize the mean square error of the actual output value and expected output value of the network.
  • other types of neural network models may also be selected according to actual needs.
  • the input layer includes n nodes
  • the hidden layer includes m nodes
  • the BP neural network model may be expressed as:
  • y is the output value of the output layer
  • the output value y of the first risk assessment model is the first assessment value
  • the output value y of the second risk assessment model is the second assessment value
  • S i is the input of the hidden layer, that is, the output of the input layer
  • W ij is the The connection weight between the input layer and the hidden layer
  • f ( ⁇ ) is the activation function in the BP neural network model, and when the hidden layer has an input, the activation function is expressed as f (S i ).
  • the activation function f (S i ) can use an S-type function (Sigmoid function), and f (S i ) can be expressed as:
  • t i may represent the connection weight between the i-th node of the hidden layer and the output layer, for example, t 1 is the first node of the hidden layer and the output layer
  • the connection weight between t 2 is the connection weight between the second node of the hidden layer and the output layer
  • t 3 is the third node of the hidden layer and the output layer connection weight between
  • t m is the weight of the connection node between the m-th hidden layer and the output layer weights.
  • W ij is the connection weight between the i-th node of the hidden layer and the j-th node of the input layer.
  • the second obtaining module 103 is used to obtain characteristic data of a pre-sale activity to be entered, and input the characteristic data to the first risk assessment model to obtain a first evaluation value, and input the characteristic data to all The second risk assessment model obtains the second assessment value.
  • the second acquisition module 103 may acquire the characteristic data of the merchant A, specifically, the first acquisition module 103 may receive the user input of the merchant A's characteristic data.
  • the characteristic data of the merchant A includes merchant registered capital information, shareholder number information, shareholder credit record information, store location city information, store location information, merchant industry information, merchandise discount strength information, discount time information, product cost information, opening time Information, merchant profit or loss information, customer number information.
  • the first risk assessment model is constructed based on the historical feature data of the pre-sale success.
  • the feature data of the merchant A is input to the first risk assessment model to obtain a first assessment value, the first assessment value It can be used to predict the probability of successful pre-sale of merchant A.
  • the second risk assessment model is constructed based on the historical feature data of pre-sale failure, therefore, the merchant A's feature data is input to the second risk assessment model to obtain a second assessment value, the second assessment value It can be used to predict the probability of failure of the pre-sale of merchant A.
  • the calculation module 104 is configured to calculate the success rate of the pre-sale activity to be performed according to the first evaluation value and the second evaluation value.
  • a first weight coefficient and a second weight coefficient may be set in advance for the first evaluation value and the second evaluation value, respectively, where the first evaluation value corresponds to the first weight coefficient, the first The second evaluation value corresponds to the second weight coefficient, and the calculation module 104 may be obtained by subtracting the product of the second evaluation value and the second weight coefficient by multiplying the product of the first evaluation value and the first weight coefficient
  • the output module 105 is configured to output first prompt information when the success rate of the pre-sale activity to be performed is greater than the preset threshold, and the success rate of the pre-sale activity to be performed is not greater than the preset threshold , The second prompt message is output.
  • the success rate of the pre-sale activity to be performed is greater than the preset threshold, it indicates that the merchant A ’s pre-sale success probability is greater than the failure probability, the merchant ’s business risk is low, and the user can participate in the merchant A ’s
  • the success rate of the pre-sale activity to be carried out is not greater than the preset threshold, it indicates that the merchant A ’s pre-sale success rate is less than the failure probability, and the merchant ’s business risk is high. It is not recommended that users participate in the merchant ’s business.
  • the preset threshold can be set and adjusted according to actual usage requirements. For example, the preset threshold is set to 0.5.
  • the first prompt message may be: the risk of pre-sale is low, you can choose to participate in the pre-sale activity of merchant A; if the pre-sale of merchant A is calculated successfully If the rate is not greater than 0.5, it means that the merchant A ’s pre-sale success probability is less than the failure probability, and a second prompt message is output to the user.
  • the second prompt message may be: the pre-sale risk is higher, and it is not recommended to participate in the merchant A ’s Pre-sale activities.
  • FIG. 4 is a schematic diagram of a preferred embodiment of the computer device of the present application.
  • the computer device 1 includes a memory 20, a processor 30, and computer-readable instructions 40 stored in the memory 20 and executable on the processor 30, such as a pre-sale risk assessment program.
  • the processor 30 executes the computer-readable instruction 40
  • the steps in the above pre-sale risk assessment method embodiment are implemented, for example, steps S11 to S14 shown in FIG. 1 and steps S11 to S17 shown in FIG. 2.
  • the processor 30 executes the computer-readable instructions 40
  • the functions of the modules in the foregoing pre-sale risk assessment system embodiment are implemented, for example, the modules 101 to 105 in FIG. 3.
  • the computer-readable instructions 40 may be divided into one or more modules / units, the one or more modules / units are stored in the memory 20 and executed by the processor 30, To complete this application.
  • the one or more modules / units may be a series of computer-readable instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer-readable instructions 40 in the computer device 1.
  • the computer-readable instructions 40 may be divided into a first acquisition module 101, a model training module 102, a second acquisition module 103, a calculation module 104, and an output module 105 in FIG. For specific functions of each module, see Embodiment 2.
  • the computer device 1 may be a computing device such as a desktop computer, a notebook, a palmtop computer and a cloud server.
  • a person skilled in the art may understand that the schematic diagram is only an example of the computer device 1 and does not constitute a limitation on the computer device 1, and may include more or less components than the illustration, or a combination of certain components, or different Components, for example, the computer device 1 may also include input and output devices, network access devices, buses, and the like.
  • the so-called processor 30 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), Ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor 30 may also be any conventional processor, etc.
  • the processor 30 is the control center of the computer device 1 and connects the entire computer device 1 using various interfaces and lines The various parts.
  • the memory 20 may be used to store the computer-readable instructions 40 and / or modules / units, and the processor 30 executes or executes the computer-readable instructions and / or modules / units stored in the memory 20, and The data stored in the memory 20 is called to realize various functions of the computer device 1.
  • the memory 20 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one function required application programs (such as sound playback function, image playback function, etc.); the storage data area may Data (such as audio data, phone book, etc.) created according to the use of the computer device 1 is stored.
  • the memory 20 may include a high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart, Media, Card, SMC), and a secure digital (SD) Card, flash memory card (Flash), at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
  • non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart, Media, Card, SMC), and a secure digital (SD) Card, flash memory card (Flash), at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
  • the module / unit integrated in the computer device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a non-volatile readable storage medium.
  • the present application can implement all or part of the processes in the methods of the above embodiments, and can also be completed by instructing relevant hardware through computer-readable instructions.
  • the computer-readable instructions can be stored in a non-volatile In reading the storage medium, when the computer-readable instructions are executed by the processor, the steps of the foregoing method embodiments may be implemented.
  • the computer readable instructions include computer readable instruction codes, and the computer readable instruction codes may be in source code form, object code form, executable file, or some intermediate form, etc.
  • the non-volatile readable medium may include: any entity or device capable of carrying the computer-readable instruction code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • electrical carrier signals telecommunications signals
  • telecommunications signals and software distribution media.
  • the content contained in the non-volatile readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in jurisdictions. For example, in some jurisdictions, according to legislation and patent practice, non- Volatile readable media does not include electrical carrier signals and telecommunication signals.
  • the functional units in the embodiments of the present application may be integrated in the same processing unit, or each unit may exist alone physically, or two or more units may be integrated in the same unit.
  • the above integrated unit can be implemented in the form of hardware, or in the form of hardware plus software function modules.

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种预售风险评估方法、系统、计算机装置及可读存储介质。所述预售风险评估方法包括：获取历史特征数据，所述历史特征数据为商户已经发起预售行为且具有预售结果的数据（S11）；将不同的预售结果所对应的历史特征数据分别输入至神经网络模型进行训练得到第一风险评估模型及第二风险评估模型（S12）；获取一待进行预售活动的特征数据，并将所述特征数据分别输入至该第一风险评估模型及第二风险评估模型，得到第一评估值及第二评估值（S13）；及根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率（S14）。所述方法基于神经网络训练得到预售风险评估模型，根据模型可计算得到商户预售成功率，避免造成用户经济损失。

Description

预售风险评估方法、系统、计算机装置及可读存储介质
本申请要求于2018年10月31日提交中国专利局，申请号为201811289813.1发明名称为“预售风险评估方法、系统、计算机装置及可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及数据处理领域，尤其涉及一种预售风险评估方法、系统、计算机装置及可读存储介质。
背景技术
预售是指在产品还没正式进入市场前进行的销售行为，可以通过预售来了解该种产品是否有市场，特别是针对一些只能通过批量化生产的产品而言，通过预售达到一定量后才投入生产，有效规避了生产存在的风险。现在商家在商品售卖前都喜欢做提前预售的营销活动，以吸引顾客。不管是那一种产品的商家，其经营都存在一定的风险，一旦商家经营不善，或者商家故意诈骗，很容易造成用户的经济损失。
本部分旨在为权利要求书及具体实施方式中陈述的本申请的实施方式提供背景或上下文。此处的描述不因为包括在本部分中就承认是现有技术。
发明内容
鉴于上述，本申请提供一种预售风险评估方法、系统、计算机装置及存储介质，其可以实现对商户预售行为进行风险预测。
本申请一实施方式提供一种预售风险评估方法，所述方法包括：
获取历史特征数据，其中所述历史特征数据为商户已经发起预售行为且具有预售结果的数据，所述预售结果包括预售成功及预售失败；
按照不同的预售结果对所述历史特征数据进行分类；
将不同的预售结果所对应的历史特征数据分别输入至神经网络模型进行训练，以分别得到对应于预售成功的第一风险评估模型及对应于预售失败的第二风险评估模型；
获取一待进行预售活动的特征数据，并将所述特征数据输入至所述第一风险评估模型得到第一评估值，及将所述特征数据输入 至所述第二风险评估模型得到第二评估值；及
根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率。
本申请一实施方式提供一种预售风险评估系统，所述系统包括：
第一获取模块，用于历史特征数据，其中所述历史特征数据为商户已经发起预售行为且具有预售结果的数据，所述预售结果包括预售成功及预售失败；
模型训练模块，用于将不同的预售结果所对应的历史特征数据分别输入至神经网络模型进行训练，以分别得到对应于预售成功的第一风险评估模型及对应于预售失败的第二风险评估模型；
第二获取模块，用于获取一待进行预售活动的特征数据，并将所述特征数据输入至所述第一风险评估模型得到第一评估值，及将所述特征数据输入至所述第二风险评估模型得到第二评估值；及
计算模块，用于根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率。
本申请一实施方式提供一种计算机装置，所述计算机装置包括处理器及存储器，所述存储器上存储有若干计算机可读指令，所述处理器用于执行存储器中存储的计算机可读指令时实现如前面所述的预售风险评估方法的步骤。
本申请一实施方式提供一种非易失性可读存储介质，其上存储有计算机可读指令，所述计算机可读指令被处理器执行时实现如前面所述的预售风险评估方法的步骤。
上述预售风险评估方法、系统、计算机装置及非易失性可读存储介质，基于机器学习与历史商户预售数据来建立并训练得到风险评估模型，并将一待进行预售活动的商户特征数据输入至所述风险评估模型计算得出该商户预售活动的成功率，进而用户可以根据该成功率判断是否需要参加该商户的预售活动，避免造成经济损失。
附图说明
图1是本申请一实施例中预售风险评估方法的步骤流程图。
图2是本申请另一实施例中预售风险评估方法的步骤流程图。
图3为本申请一实施例中预售风险评估系统的功能模块图。
图4为本申请一实施例中计算机装置示意图。
具体实施方式
为了能够更清楚地理解本申请的上述目的、特征和优点，下面 结合附图和具体实施方式对本申请进行详细描述。需要说明的是，在不冲突的情况下，本申请的实施方式及实施方式中的特征可以相互组合。
在下面的描述中阐述了很多具体细节以便于充分理解本申请，所描述的实施方式仅仅是本申请一部分实施方式，而不是全部的实施方式。基于本申请中的实施方式，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施方式，都属于本申请保护的范围。
除非另有定义，本文所使用的所有的技术和科学术语与属于本申请的技术领域的技术人员通常理解的含义相同。本文中在本申请的说明书中所使用的术语只是为了描述具体的实施方式的目的，不是旨在于限制本申请。
优选地，本申请的预售风险评估方法应用在一个或者多个计算机装置中。所述计算机装置是一种能够按照事先设定或存储的指令，自动进行数值计算和/或信息处理的设备，其硬件包括但不限于微处理器、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程门阵列(Field－Programmable Gate Array，FPGA)、数字处理器(Digital Signal Processor，DSP)、嵌入式设备等。
所述计算机装置可以是桌上型计算机、笔记本电脑、平板电脑、服务器等计算设备。所述计算机装置可以与用户通过键盘、鼠标、遥控器、触摸板或声控设备等方式进行人机交互。
实施例一：
图1是本申请预售风险评估方法较佳实施例的步骤流程图。根据不同的需求，所述流程图中步骤的顺序可以改变，某些步骤可以省略。
参阅图1所示，所述预售风险评估方法具体包括以下步骤。
步骤S11、获取历史特征数据，其中所述历史特征数据为商户已经发起预售行为且具有预售结果的数据，所述预售结果包括预售成功及预售失败。
在一实施方式中，可以通过接入网络来连接至一商户数据样本库，进而来获取与商户预售相关的历史特征数据。所述商户数据样本库可以通过大数据方式搜集多个商户进行过预售活动的历史特征数据，也可以通过接收人为录入的与商户预售相关的历史特征数据。
在一实施方式中，与商户预售相关的历史特征数据包括但不限于多个商户维度信息，多个所述商户维度信息包括但不限于：商户注册资金信息、股东人数信息、股东信用记录信息、门店所 在城市信息、门店位置信息、商户所属行业信息、商品优惠力度信息、优惠时间信息、商品成本信息、开业时间信息、商户盈利或亏损信息、顾客数量信息。
在一实施方式中，获取与商户预售相关的历史特征数据之后，还可以对获取得到特征数据进行预处理操作。可以理解地，所述历史特征数据中可能会存在一个或多个缺失数据信息的商户维度信息，为了提高后续数据处理结果的准确性，可将对应缺失数据信息的商户维度信息设置为预设默认值。例如，对于商户维度信息为商品优惠力度信息而言，若一商户的历史特征数据没有商品优惠力度信息，表示该商户在进行预售活动时没有优惠，此时，可以将该商户的商品优惠力度信息设置为预设默认值(假设预设默认值为0)。
可以理解地，与商户预售相关的历史特征数据可从结构化的商户数据样本库获取，此时获取得到的历史特征数据可直接进行后续的处理。在其他实施方式中，与商户预售相关的历史特征数据也可以是可能是非结构化的数据，如存储于文本中的数据。因而，在对所述历史特征数据进行预处理时，还可从非结构化的数据中获取对应的特征数据。
在一实施方式中，当所述历史特征数据是非结构化的数据时，可先定义与商户维度信息对应的关键词，如多个所述商户维度信息包括：商户注册资金信息、股东人数信息、股东信用记录信息、门店所在城市信息、门店位置信息、商户所属行业信息、商品优惠力度信息、优惠时间信息、商品成本信息、开业时间信息；则与该些商户维度信息对应的关键词为：注册资金、股东人数、股东信用记录、城市、位置、行业、优惠力度、优惠时间、成本、开业时间。例如，非结构化的数据包含“优惠时间为2017年1月1日”，由于其包含了关键词“优惠时间”，因而可根据关键词“优惠时间”得到对应的特征数据为“2017年1月1日”。
步骤S12、将不同的预售结果所对应的历史特征数据分别输入至神经网络模型进行训练，以分别得到对应于预售成功的第一风险评估模型及对应于预售失败的第二风险评估模型。
在一实施方式中，可以将历史特征数据按照预售结果为预售成功及预售失败来进行分类，将预售成功的历史特征数据作为第一样本数据集，将预售失败的历史特征数据作为第二样本数据集。
在一实施方式中，所述第一风险评估模型、所述第二风险评估模型可以是基于神经网络模型和第一样本数据集、第二样本数据集训练出来的模型。所述神经网络模型能够从信息处理角度对人脑神经元网络进行抽象，按不同的连接方式组成不同的网络， 无需事先确定输入与输出之间映射关系的数学方程，仅通过自身的训练，在给定输入值时得到最接近期望输出值的结果。所述神经网络模型包括输入层、隐藏层及输出层。所述历史特征数据可作为神经网络模型的输入层，再经过神经网络模型的隐藏层的连接后由输出层输出一评估值。
在一实施方式中，由于所述预售结果包括预售成功及预售失败，可以将预售结果为预售成功的历史特征数据输入至第一神经网络模型进行训练，得到所述第一风险评估模型，将预售结果为预售失败的历史特征数据输入至第二神经网络模型进行训练，得到所述第二风险评估模型。所述神经网络模型可以是BP(Back Propagation、反向传播)神经网络模型，所述BP神经网络模型是一种基于梯度下降法的按误差反向传播训练的多层前馈网络，利用梯度搜索技术，以期使网络的实际输出值和期望输出值的误差均方差为最小。在本申请的其他实施方式中，也可以根据实际需要选择其他类型的神经网络模型。
在一实施方式中，所述输入层包括n个节点，所述隐藏层包括m个节点，所述BP神经网络模型可以表示为：
Figure PCTCN2019077514-appb-000001
其中，y为所述输出层的输出值，当将所述特征数据输入至所述第一风险评估模型时，所述第一风险评估模型的输出值y为所述第一评估值，当将所述特征数据输入至所述第二风险评估模型时，所述第二风险评估模型的输出值y为所述第二评估值，t i为所述隐藏层与所述输出层之间的连接权重，
Figure PCTCN2019077514-appb-000002
(i＝1,2,3...m；j＝1,2,3...n)，S i为所述隐藏层的输入，即为所述输入层的输出，W ij为所述输入层与所述隐藏层之间的连接权重，f(·)为所述BP神经网络模型中的激活函数，当所述隐含层有输入时，激活函数表示为f(S i)。所述激活函数f(S i)可以使用S型函数(Sigmoid函数)，f(S i)可以表示为：
Figure PCTCN2019077514-appb-000003
可以理解地，t i可以表示所述隐含层的第i个节点与所述输出层之间的连接权重，例如，t 1即为所述隐含层的第1个节点与所述输出层之间的连接权重，t 2即为所述隐含层的第2个节点与所述输出层之间的连接权重，t 3即为所述隐含层的第3个节点与所述输出层之间的连接权重，t m即为所述隐含层的第m个节点与所述输出层之间的连接权重。同理可知，W ij即为所述隐含层的第i个节点与所述输入层的第j个节点之间的连接权重。通过对所述BP神经网络模型进行训练，可以相应地得到t i和W ij的值，即训练得到BP神经网络模型各个层的参数，如此可得到风险评估模型。
步骤S13、获取一待进行预售活动的特征数据，并将所述特征 数据输入至所述第一风险评估模型得到第一评估值，及将所述特征数据输入至所述第二风险评估模型得到第二评估值。
在一实施方式中，当一商户A准备开展预售活动时，可以获取该商户A的特征数据，该商户A的特征数据包括商户注册资金信息、股东人数信息、股东信用记录信息、门店所在城市信息、门店位置信息、商户所属行业信息、商品优惠力度信息、优惠时间信息、商品成本信息、开业时间信息、商户盈利或亏损信息、顾客数量信息。所述第一风险评估模型是基于预售成功的历史特征数据而构建的，因此，将该商户A的特征数据输入至所述第一风险评估模型得到第一评估值，所述第一评估值可以用来预测该商户A预售成功的机率。所述第二风险评估模型是基于预售失败的历史特征数据而构建的，因此，将该商户A的特征数据输入至所述第二风险评估模型得到第二评估值，所述第二评估值可以用来预测该商户A预售失败的机率。
步骤S14、根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率。
在一实施方式中，可以预先为所述第一评估值及所述第二评估值分别设置第一权重系数及第二权重系数，其中所述第一评估值对应第一权重系数，所述第二评估值对应第二权重系数，再将所述第一评估值与所述第一权重系数的乘积减去所述第二评估值与所述第二权重系数的乘积得到该商户A待进行的预售活动的成功率(计算公式可以是：成功率＝第一评估值*第一权重系数-第二评估值*第二权重系数)。
请同时参阅图2，与图1示出的预售风险评估方法相比，图2示出的预售风险评估方法还包括步骤S15、S16及S17。
步骤S15，判断所述待进行预售活动的成功率是否大于预设阈值；
步骤S16，当所述待进行预售活动的成功率大于所述预设阈值时，输出第一提示信息；
步骤S17，当所述待进行预售活动的成功率不大于所述预设阈值时，输出第二提示信息。
在一实施方式中，当所述待进行预售活动的成功率大于所述预设阈值时，表明该商户A预售的成功机率大于失败机率，商户经营风险较低，用户可以参加该商户A的预售活动，当所述待进行预售活动的成功率不大于所述预设阈值时，表明该商户A预售的成功机率小于失败机率，商户经营风险较大，不建议用户参加该商户A的预售活动。所述预设阈值可以根据实际使用需求进行设定与调整，例如，所述预设阈值设置为0.5，若计算得到该商户 A预售的成功率大于0.5，则表示所述商户A预售的成功机率大于失败机率，输出第一提示信息给用户，所述第一提示信息可以是：预售风险较低，可选择参加该商户A的预售活动；若计算得到该商户A预售的成功率不大于0.5，则表示所述商户A预售的成功机率小于失败机率，输出第二提示信息给用户，所述第二提示信息可以是：预售风险较高，不建议参加该商户A的预售活动。
实施例二：
图3为本申请预售风险评估系统较佳实施例的功能模块图。
参阅图2所示，所述预售风险评估系统10可以包括第一获取模块101、模型训练模块102、第二获取模块103、计算模块104及输出模块105。
所述获取模块101用于历史特征数据，其中所述历史特征数据为商户已经发起预售行为且具有预售结果的数据，所述预售结果包括预售成功及预售失败。
在一实施方式中，所述获取模块101可以通过接入网络来连接至一商户数据样本库，进而来获取与商户预售相关的历史特征数据。所述商户数据样本库可以通过大数据方式搜集多个商户进行过预售活动的历史特征数据，也可以通过接收人为录入的与商户预售相关的历史特征数据。
在一实施方式中，与商户预售相关的历史特征数据包括但不限于多个商户维度信息，多个所述商户维度信息包括但不限于：商户注册资金信息、股东人数信息、股东信用记录信息、门店所在城市信息、门店位置信息、商户所属行业信息、商品优惠力度信息、优惠时间信息、商品成本信息、开业时间信息、商户盈利或亏损信息、顾客数量信息。
在一实施方式中，所述获取模块101在获取与商户预售相关的历史特征数据之后，还可以对获取得到特征数据进行预处理操作。可以理解地，所述历史特征数据中可能会存在一个或多个缺失数据信息的商户维度信息，为了提高后续数据处理结果的准确性，可将对应缺失数据信息的商户维度信息设置为预设默认值。例如，对于商户维度信息为商品优惠力度信息而言，若一商户的历史特征数据没有商品优惠力度信息，表示该商户在进行预售活动时没有优惠，此时，可以将该商户的商品优惠力度信息设置为预设默认值(假设预设默认值为0)。
可以理解地，与商户预售相关的历史特征数据可从结构化的商户数据样本库获取，此时获取得到的历史特征数据可直接进行后续的处理。在其他实施方式中，与商户预售相关的历史特征数据也可以是可能是非结构化的数据，如存储于文本中的数据。因而， 在对所述历史特征数据进行预处理时，还可从非结构化的数据中获取对应的特征数据。
在一实施方式中，当所述历史特征数据是非结构化的数据时，可先定义与商户维度信息对应的关键词，如多个所述商户维度信息包括：商户注册资金信息、股东人数信息、股东信用记录信息、门店所在城市信息、门店位置信息、商户所属行业信息、商品优惠力度信息、优惠时间信息、商品成本信息、开业时间信息；则与该些商户维度信息对应的关键词为：注册资金、股东人数、股东信用记录、城市、位置、行业、优惠力度、优惠时间、成本、开业时间。例如，非结构化的数据包含“优惠时间为2017年1月1日”，由于其包含了关键词“优惠时间”，因而可根据关键词“优惠时间”得到对应的特征数据为“2017年1月1日”。
所述模型训练模块102用于将不同的预售结果所对应的历史特征数据分别输入至神经网络模型进行训练，以分别得到对应于预售成功的第一风险评估模型及对应于预售失败的第二风险评估模型。
在一实施方式中，所述历史特征数据可以按照预售结果为预售成功及预售失败来进行分类，将预售成功的历史特征数据作为第一样本数据集，将预售失败的历史特征数据作为第二样本数据集。
在一实施方式中，所述第一风险评估模型、所述第二风险评估模型可以是基于神经网络模型和第一样本数据集、第二样本数据集训练出来的模型。所述神经网络模型能够从信息处理角度对人脑神经元网络进行抽象，按不同的连接方式组成不同的网络，无需事先确定输入与输出之间映射关系的数学方程，仅通过自身的训练，在给定输入值时得到最接近期望输出值的结果。所述神经网络模型包括输入层、隐藏层及输出层。所述历史特征数据可作为神经网络模型的输入层，再经过神经网络模型的隐藏层的连接后由输出层输出一评估值。
在一实施方式中，由于所述预售结果包括预售成功及预售失败，所述模型训练模块102可以将预售结果为预售成功的历史特征数据输入至第一神经网络模型进行训练，得到所述第一风险评估模型，将预售结果为预售失败的历史特征数据输入至第二神经网络模型进行训练，得到所述第二风险评估模型。所述神经网络模型可以是BP(Back Propagation、反向传播)神经网络模型，所述BP神经网络模型是一种基于梯度下降法的按误差反向传播训练的多层前馈网络，利用梯度搜索技术，以期使网络的实际输出值和期望输出值的误差均方差为最小。在本申请的其他实施方式中， 也可以根据实际需要选择其他类型的神经网络模型。
在一实施方式中，所述输入层包括n个节点，所述隐藏层包括m个节点，所述BP神经网络模型可以表示为：
Figure PCTCN2019077514-appb-000004
其中，y为所述输出层的输出值，当将所述特征数据输入至所述第一风险评估模型时，所述第一风险评估模型的输出值y为所述第一评估值，当将所述特征数据输入至所述第二风险评估模型时，所述第二风险评估模型的输出值y为所述第二评估值，t i为所述隐藏层与所述输出层之间的连接权重，
Figure PCTCN2019077514-appb-000005
(i＝1,2,3...m；j＝1,2,3...n)，S i为所述隐藏层的输入，即为所述输入层的输出，W ij为所述输入层与所述隐藏层之间的连接权重，f(·)为所述BP神经网络模型中的激活函数，当所述隐含层有输入时，激活函数表示为f(S i)。所述激活函数f(S i)可以使用S型函数(Sigmoid函数)，f(S i)可以表示为：
Figure PCTCN2019077514-appb-000006
可以理解地，t i可以表示所述隐含层的第i个节点与所述输出层之间的连接权重，例如，t 1即为所述隐含层的第1个节点与所述输出层之间的连接权重，t 2即为所述隐含层的第2个节点与所述输出层之间的连接权重，t 3即为所述隐含层的第3个节点与所述输出层之间的连接权重，t m即为所述隐含层的第m个节点与所述输出层之间的连接权重。同理可知，W ij即为所述隐含层的第i个节点与所述输入层的第j个节点之间的连接权重。通过对所述BP神经网络模型进行训练，可以相应地得到t i和W ij的值，即训练得到BP神经网络模型各个层的参数，如此可得到风险评估模型。
所述第二获取模块103用于获取一待进行预售活动的特征数据，并将所述特征数据输入至所述第一风险评估模型得到第一评估值，及将所述特征数据输入至所述第二风险评估模型得到第二评估值。
在一实施方式中，当一商户A准备开展预售活动时，第二获取模块103可以获取该商户A的特征数据，具体地，可以是第获取模块103接收用户输入该商户A的特征数据。该商户A的特征数据包括商户注册资金信息、股东人数信息、股东信用记录信息、门店所在城市信息、门店位置信息、商户所属行业信息、商品优惠力度信息、优惠时间信息、商品成本信息、开业时间信息、商户盈利或亏损信息、顾客数量信息。所述第一风险评估模型是基于预售成功的历史特征数据而构建的，因此，将该商户A的特征数据输入至所述第一风险评估模型得到第一评估值，所述第一评估值可以用来预测该商户A预售成功的机率。所述第二风险评估模型是基于预售失败的历史特征数据而构建的，因此，将该商户A 的特征数据输入至所述第二风险评估模型得到第二评估值，所述第二评估值可以用来预测该商户A预售失败的机率。
所述计算模块104用于根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率。
在一实施方式中，可以预先为所述第一评估值及所述第二评估值分别设置第一权重系数及第二权重系数，其中所述第一评估值对应第一权重系数，所述第二评估值对应第二权重系数，所述计算模块104可以通过将所述第一评估值与所述第一权重系数的乘积减去所述第二评估值与所述第二权重系数的乘积得到该商户A待进行的预售活动的成功率(计算公式可以是：成功率＝第一评估值*第一权重系数-第二评估值*第二权重系数)。
所述输出模块105用于在所述待进行预售活动的成功率大于所述预设阈值时，输出第一提示信息，在所述待进行预售活动的成功率不大于所述预设阈值时，输出第二提示信息。
在一实施方式中，当所述待进行预售活动的成功率大于所述预设阈值时，表明该商户A预售的成功机率大于失败机率，商户经营风险较低，用户可以参加该商户A的预售活动，当所述待进行预售活动的成功率不大于所述预设阈值时，表明该商户A预售的成功机率小于失败机率，商户经营风险较大，不建议用户参加该商户A的预售活动。所述预设阈值可以根据实际使用需求进行设定与调整，例如，所述预设阈值设置为0.5，若计算得到该商户A预售的成功率大于0.5，则表示所述商户A预售的成功机率大于失败机率，输出第一提示信息给用户，所述第一提示信息可以是：预售风险较低，可选择参加该商户A的预售活动；若计算得到该商户A预售的成功率不大于0.5，则表示所述商户A预售的成功机率小于失败机率，输出第二提示信息给用户，所述第二提示信息可以是：预售风险较高，不建议参加该商户A的预售活动。
图4为本申请计算机装置较佳实施例的示意图。
所述计算机装置1包括存储器20、处理器30以及存储在所述存储器20中并可在所述处理器30上运行的计算机可读指令40，例如预售风险评估程序。所述处理器30执行所述计算机可读指令40时实现上述预售风险评估方法实施例中的步骤，例如图1所示的步骤S11～S14、图2所示的步骤S11～S17。或者，所述处理器30执行所述计算机可读指令40时实现上述预售风险评估系统实施例中各模块的功能，例如图3中的模块101～105。
示例性的，所述计算机可读指令40可以被分割成一个或多个模块/单元，所述一个或者多个模块/单元被存储在所述存储器20中，并由所述处理器30执行，以完成本申请。所述一个或多个模 块/单元可以是能够完成特定功能的一系列计算机可读指令段，所述指令段用于描述所述计算机可读指令40在所述计算机装置1中的执行过程。例如，所述计算机可读指令40可以被分割成图3中的第一获取模块101、模型训练模块102、第二获取模块103、计算模块104及输出模块105。各模块具体功能参见实施例二。
所述计算机装置1可以是桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。本领域技术人员可以理解，所述示意图仅仅是计算机装置1的示例，并不构成对计算机装置1的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述计算机装置1还可以包括输入输出设备、网络接入设备、总线等。
所称处理器30可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者所述处理器30也可以是任何常规的处理器等，所述处理器30是所述计算机装置1的控制中心，利用各种接口和线路连接整个计算机装置1的各个部分。
所述存储器20可用于存储所述计算机可读指令40和/或模块/单元，所述处理器30通过运行或执行存储在所述存储器20内的计算机可读指令和/或模块/单元，以及调用存储在存储器20内的数据，实现所述计算机装置1的各种功能。所述存储器20可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据计算机装置1的使用所创建的数据(比如音频数据、电话本等)等。此外，存储器20可以包括高速随机存取存储器，还可以包括非易失性存储器，例如硬盘、内存、插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)、至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
所述计算机装置1集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个非易失性可读取存储介质中。基于这样的理解，本申请实现上述实施例方法中的全部或部分流程，也可以通过计算机可读指令来指令相关的硬件来完成，所述的计算机可读指令可存储于一非易失性可读存储介质中，所述计算机可读指令在被处理器执行时，可实现 上述各个方法实施例的步骤。其中，所述计算机可读指令包括计算机可读指令代码，所述计算机可读指令代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述非易失性可读介质可以包括：能够携带所述计算机可读指令代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、电载波信号、电信信号以及软件分发介质等。需要说明的是，所述非易失性可读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，非易失性可读介质不包括电载波信号和电信信号。
在本申请所提供的几个实施例中，应该理解到，所揭露的计算机装置和方法，可以通过其它的方式实现。例如，以上所描述的计算机装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
另外，在本申请各个实施例中的各功能单元可以集成在相同处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在相同单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能模块的形式实现。
对于本领域技术人员而言，显然本申请不限于上述示范性实施例的细节，而且在不背离本申请的精神或基本特征的情况下，能够以其他的具体形式实现本申请。因此，无论从哪一点来看，均应将实施例看作是示范性的，而且是非限制性的，本申请的范围由所附权利要求而不是上述说明限定，因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附图标记视为限制所涉及的权利要求。此外，显然“包括”一词不排除其他单元或步骤，单数不排除复数。计算机装置权利要求中陈述的多个单元或计算机装置也可以由同一个单元或计算机装置通过软件或者硬件来实现。第一，第二等词语用来表示名称，而并不表示任何特定的顺序。
最后应说明的是，以上实施例仅用以说明本申请的技术方案而非限制，尽管参照较佳实施例对本申请进行了详细说明，本领域的普通技术人员应当理解，可以对本申请的技术方案进行修改或等同替换，而不脱离本申请技术方案的精神和范围。

Claims (20)

  1. 一种预售风险评估方法，其特征在于，所述方法包括：
    获取历史特征数据，其中所述历史特征数据为商户已经发起预售行为且具有预售结果的数据，所述预售结果包括预售成功及预售失败；
    将不同的预售结果所对应的历史特征数据分别输入至神经网络模型进行训练，以分别得到对应于预售成功的第一风险评估模型及对应于预售失败的第二风险评估模型；
    获取一待进行预售活动的特征数据，并将所述特征数据输入至所述第一风险评估模型得到第一评估值，及将所述特征数据输入至所述第二风险评估模型得到第二评估值；及
    根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率。
  2. 如权利要求1所述的预售风险评估方法，其特征在于，所述历史特征数据包括多个商户维度信息，多个所述商户维度信息包括但不限于：商户注册资金信息、股东人数信息、股东信用记录信息、门店所在城市信息、门店位置信息、商户所属行业信息、商品优惠力度信息、优惠时间信息、商品成本信息、开业时间信息、商户盈利或亏损信息、顾客数量信息。
  3. 如权利要求2所述的预售风险评估方法，其特征在于，所述获取历史特征数据的步骤之后还包括：
    判断是否存在一个或者多个商户维度信息缺失；及
    当存在一个或者多个商户维度信息缺失，将缺失的一个或者多个商户维度信息设置为预设特征数据。
  4. 如权利要求1或2所述的预售风险评估方法，其特征在于，所述将不同的预售结果所对应的历史特征数据分别输入至神经网络模型进行训练，以分别得到对应于预售成功的第一风险评估模型及对应于预售失败的第二风险评估模型的步骤包括：
    将预售结果为预售成功的历史特征数据输入至第一神经网络模型进行训练，得到所述第一风险评估模型；
    将预售结果为预售失败的历史特征数据输入至第二神经网络模型进行训练，得到所述第二风险评估模型；
    其中，所述第一神经网络模型及所述第二神经网络模型均为BP神经网络模型，所述BP神经网络模型包括输入层、隐藏层及输出层。
  5. 如权利要求4所述的预售风险评估方法，其特征在于，所述 输入层包括n个节点，所述隐藏层包括m个节点，所述BP神经网络模型为：
    Figure PCTCN2019077514-appb-100001
    其中，y为所述输出层的输出值，当将所述特征数据输入至所述第一风险评估模型时，所述第一风险评估模型的输出值y为所述第一评估值，当将所述特征数据输入至所述第二风险评估模型时，所述第二风险评估模型的输出值y为所述第二评估值，t i为所述隐藏层与所述输出层之间的连接权重，
    Figure PCTCN2019077514-appb-100002
    (i＝1,2,3...m；j＝1,2,3...n)为所述隐藏层的输入，即为所述输入层的输出，W ij为所述输入层与所述隐藏层之间的连接权重；f(S i)为所述BP神经网络模型中的激活函数，
    Figure PCTCN2019077514-appb-100003
  6. 如权利要求1所述的预售风险评估方法，其特征在于，所述根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率的步骤包括：
    获取所述第一评估值对应的第一权重系数及所述第二评估值对应的第二权重系数；及
    将所述第一评估值与所述第一权重系数的乘积减去所述第二评估值与所述第二权重系数的乘积得到所述待进行预售活动的成功率。
  7. 如权利要求6所述的预售风险评估方法，其特征在于，所述根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率的步骤之后还包括：
    判断所述待进行预售活动的成功率是否大于预设阈值；
    当所述待进行预售活动的成功率大于所述预设阈值时，输出第一提示信息；及
    当所述待进行预售活动的成功率不大于所述预设阈值时，输出第二提示信息。
  8. 一种预售风险评估系统，其特征在于，所述系统包括：
    第一获取模块，用于历史特征数据，其中所述历史特征数据为商户已经发起预售行为且具有预售结果的数据，所述预售结果包括预售成功及预售失败；
    模型训练模块，用于将不同的预售结果所对应的历史特征数据分别输入至神经网络模型进行训练，以分别得到对应于预售成功的第一风险评估模型及对应于预售失败的第二风险评估模型；
    第二获取模块，用于获取一待进行预售活动的特征数据，并将所述特征数据输入至所述第一风险评估模型得到第一评估值，及将所述特征数据输入至所述第二风险评估模型得到第二评估值；及
    计算模块，用于根据所述第一评估值及所述第二评估值计算得 出所述待进行预售活动的成功率。
  9. 一种计算机装置，所述计算机装置包括处理器及存储器，所述存储器上存储有若干计算机可读指令，其特征在于，所述处理器执行存储器中存储的计算机可读指令时实现以下步骤：
    获取历史特征数据，其中所述历史特征数据为商户已经发起预售行为且具有预售结果的数据，所述预售结果包括预售成功及预售失败；
    将不同的预售结果所对应的历史特征数据分别输入至神经网络模型进行训练，以分别得到对应于预售成功的第一风险评估模型及对应于预售失败的第二风险评估模型；
    获取一待进行预售活动的特征数据，并将所述特征数据输入至所述第一风险评估模型得到第一评估值，及将所述特征数据输入至所述第二风险评估模型得到第二评估值；及
    根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率。
  10. 如权利要求9所述的计算机装置，其特征在于，所述历史特征数据包括多个商户维度信息，多个所述商户维度信息包括但不限于：商户注册资金信息、股东人数信息、股东信用记录信息、门店所在城市信息、门店位置信息、商户所属行业信息、商品优惠力度信息、优惠时间信息、商品成本信息、开业时间信息、商户盈利或亏损信息、顾客数量信息。
  11. 如权利要求10所述的计算机装置，其特征在于，所述处理器在所述获取历史特征数据时，执行所述计算机可读指令以实现以下步骤：
    判断是否存在一个或者多个商户维度信息缺失；及
    当存在一个或者多个商户维度信息缺失，将缺失的一个或者多个商户维度信息设置为预设特征数据。
  12. 如权利要求9或10所述的计算机装置，其特征在于，所述处理器在所述将不同的预售结果所对应的历史特征数据分别输入至神经网络模型进行训练，以分别得到对应于预售成功的第一风险评估模型及对应于预售失败的第二风险评估模型时，执行所述计算机可读指令以实现以下步骤：
    将预售结果为预售成功的历史特征数据输入至第一神经网络模型进行训练，得到所述第一风险评估模型；
    将预售结果为预售失败的历史特征数据输入至第二神经网络模型进行训练，得到所述第二风险评估模型；
    其中，所述第一神经网络模型及所述第二神经网络模型均为BP神经网络模型，所述BP神经网络模型包括输入层、隐藏层及 输出层。
  13. 如权利要求9所述的计算机装置，其特征在于，所述处理器在所述根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率时，执行所述计算机可读指令以实现以下步骤：
    获取所述第一评估值对应的第一权重系数及所述第二评估值对应的第二权重系数；及
    将所述第一评估值与所述第一权重系数的乘积减去所述第二评估值与所述第二权重系数的乘积得到所述待进行预售活动的成功率。
  14. 如权利要求13所述的计算机装置，其特征在于，所述处理器在所述根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率时，执行所述计算机可读指令以实现以下步骤：
    判断所述待进行预售活动的成功率是否大于预设阈值；
    当所述待进行预售活动的成功率大于所述预设阈值时，输出第一提示信息；及
    当所述待进行预售活动的成功率不大于所述预设阈值时，输出第二提示信息。
  15. 一种非易失性可读存储介质，其上存储有计算机可读指令，其特征在于，所述计算机可读指令被处理器执行时实现以下步骤：
    获取历史特征数据，其中所述历史特征数据为商户已经发起预售行为且具有预售结果的数据，所述预售结果包括预售成功及预售失败；
    将不同的预售结果所对应的历史特征数据分别输入至神经网络模型进行训练，以分别得到对应于预售成功的第一风险评估模型及对应于预售失败的第二风险评估模型；
    获取一待进行预售活动的特征数据，并将所述特征数据输入至所述第一风险评估模型得到第一评估值，及将所述特征数据输入至所述第二风险评估模型得到第二评估值；及
    根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率。
  16. 如权利要求15所述的存储介质，其特征在于，所述历史特征数据包括多个商户维度信息，多个所述商户维度信息包括但不限于：商户注册资金信息、股东人数信息、股东信用记录信息、门店所在城市信息、门店位置信息、商户所属行业信息、商品优惠力度信息、优惠时间信息、商品成本信息、开业时间信息、商户盈利或亏损信息、顾客数量信息。
  17. 如权利要求16所述的存储介质，其特征在于，在所述获取历史特征数据时，所述计算机可读指令被所述处理器执行以实现以下步骤：
    判断是否存在一个或者多个商户维度信息缺失；及
    当存在一个或者多个商户维度信息缺失，将缺失的一个或者多个商户维度信息设置为预设特征数据。
  18. 如权利要求15或16所述的存储介质，其特征在于，在所述将不同的预售结果所对应的历史特征数据分别输入至神经网络模型进行训练，以分别得到对应于预售成功的第一风险评估模型及对应于预售失败的第二风险评估模型时，所述计算机可读指令被所述处理器执行以实现以下步骤：
    将预售结果为预售成功的历史特征数据输入至第一神经网络模型进行训练，得到所述第一风险评估模型；
    将预售结果为预售失败的历史特征数据输入至第二神经网络模型进行训练，得到所述第二风险评估模型；
    其中，所述第一神经网络模型及所述第二神经网络模型均为BP神经网络模型，所述BP神经网络模型包括输入层、隐藏层及输出层。
  19. 如权利要求15所述的存储介质，其特征在于，在所述根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率时，所述计算机可读指令被所述处理器执行以实现以下步骤：
    获取所述第一评估值对应的第一权重系数及所述第二评估值对应的第二权重系数；及
    将所述第一评估值与所述第一权重系数的乘积减去所述第二评估值与所述第二权重系数的乘积得到所述待进行预售活动的成功率。
  20. 如权利要求19所述的存储介质，其特征在于，在所述根据所述第一评估值及所述第二评估值计算得出所述待进行预售活动的成功率时，所述计算机可读指令被所述处理器执行以实现以下步骤：
    判断所述待进行预售活动的成功率是否大于预设阈值；
    当所述待进行预售活动的成功率大于所述预设阈值时，输出第一提示信息；及
    当所述待进行预售活动的成功率不大于所述预设阈值时，输出第二提示信息。
PCT/CN2019/077514 2018-10-31 2019-03-08 预售风险评估方法、系统、计算机装置及可读存储介质 Ceased WO2020087828A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811289813.1A CN109598410A (zh) 2018-10-31 2018-10-31 预售风险评估方法、系统、计算机装置及可读存储介质
CN201811289813.1 2018-10-31

Publications (1)

Publication Number Publication Date
WO2020087828A1 true WO2020087828A1 (zh) 2020-05-07

Family

ID=65957263

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/077514 Ceased WO2020087828A1 (zh) 2018-10-31 2019-03-08 预售风险评估方法、系统、计算机装置及可读存储介质

Country Status (2)

Country Link
CN (1) CN109598410A (zh)
WO (1) WO2020087828A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115390797A (zh) * 2022-09-19 2022-11-25 中国农业银行股份有限公司 一种分数确定方法、装置、设备及存储介质
CN116342161A (zh) * 2023-03-22 2023-06-27 深圳兔展智能科技有限公司 针对客户流失的数据处理方法、装置、设备及存储介质
CN121073232A (zh) * 2025-11-10 2025-12-05 物产中大数字安全科技(浙江)有限公司 一种基于多维特征量化的商户风险识别方法及系统

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110599241A (zh) * 2019-08-22 2019-12-20 深圳市元征科技股份有限公司 一种营销方案推荐方法及装置
CN111125071A (zh) * 2019-11-25 2020-05-08 珠海格力电器股份有限公司 实时数据可信度的评估方法、装置及存储介质
CN113763019A (zh) * 2021-01-28 2021-12-07 北京沃东天骏信息技术有限公司 一种用户信息管理方法和装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103366190A (zh) * 2013-07-26 2013-10-23 中国科学院自动化研究所 一种识别交通标志的方法
CN106960266A (zh) * 2016-01-11 2017-07-18 阿里巴巴集团控股有限公司 一种预售物品的物流控制方法以及装置
CN107025597A (zh) * 2016-07-20 2017-08-08 平安科技（深圳）有限公司 基于大数据的风险预测方法和装置
CN107679557A (zh) * 2017-09-19 2018-02-09 平安科技（深圳）有限公司 驾驶模型训练方法、驾驶人识别方法、装置、设备及介质
US9898779B2 (en) * 2008-03-28 2018-02-20 American Express Travel Related Services Company, Inc. Consumer behaviors at lender level

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9898779B2 (en) * 2008-03-28 2018-02-20 American Express Travel Related Services Company, Inc. Consumer behaviors at lender level
CN103366190A (zh) * 2013-07-26 2013-10-23 中国科学院自动化研究所 一种识别交通标志的方法
CN106960266A (zh) * 2016-01-11 2017-07-18 阿里巴巴集团控股有限公司 一种预售物品的物流控制方法以及装置
CN107025597A (zh) * 2016-07-20 2017-08-08 平安科技（深圳）有限公司 基于大数据的风险预测方法和装置
CN107679557A (zh) * 2017-09-19 2018-02-09 平安科技（深圳）有限公司 驾驶模型训练方法、驾驶人识别方法、装置、设备及介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115390797A (zh) * 2022-09-19 2022-11-25 中国农业银行股份有限公司 一种分数确定方法、装置、设备及存储介质
CN116342161A (zh) * 2023-03-22 2023-06-27 深圳兔展智能科技有限公司 针对客户流失的数据处理方法、装置、设备及存储介质
CN121073232A (zh) * 2025-11-10 2025-12-05 物产中大数字安全科技(浙江)有限公司 一种基于多维特征量化的商户风险识别方法及系统

Also Published As

Publication number Publication date
CN109598410A (zh) 2019-04-09

Similar Documents

Publication Publication Date Title
CN111325353B (zh) 训练数据集的供应商选择方法、装置、设备及存储介质
WO2020087828A1 (zh) 预售风险评估方法、系统、计算机装置及可读存储介质
US20230274332A1 (en) Method and apparatus for generating recommendation reason, and storage medium
US10922633B2 (en) Utilizing econometric and machine learning models to maximize total returns for an entity
US10636057B2 (en) Method and apparatus for dynamically selecting content for online visitors
CN112966189B (zh) 一种基金产品推荐系统
CA3070612A1 (en) Click rate estimation
CN109213936B (zh) 商品搜索方法和装置
US11861698B2 (en) Vehicle selection platform
US11847599B1 (en) Computing system for automated evaluation of process workflows
CN114187119A (zh) 一种应用于保险的数据处理方法及装置
US11631094B2 (en) Pre-computing data metrics using neural networks
US10242068B1 (en) Methods and systems for ranking leads based on given characteristics
CN117813617A (zh) 基于人工智能的编排
US20160328810A1 (en) Systems and methods for communications regarding a management and scoring tool and search platform
CN118070897A (zh) 营销话术的生成方法、电子设备和存储介质
CN112766019B (zh) 一种数据处理方法、信息推荐方法和相关装置
EP4594922A1 (en) Semi-supervised system for domain specific sentiment learning
CN113779967B (zh) 企业转型信息生成方法及装置、存储介质、电子设备
CN114036267B (zh) 对话方法及系统
US10860593B1 (en) Methods and systems for ranking leads based on given characteristics
CN113205338A (zh) 基于人工智能的外汇业务处理方法及装置
WO2025213865A1 (zh) 一种数据处理方法、装置、电子设备及存储介质
CN112784861A (zh) 相似度的确定方法、装置、电子设备和存储介质
CN114119207B (zh) 特征筛选方法、预警方法、装置、电子设备、介质和程序

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19878417

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19878417

Country of ref document: EP

Kind code of ref document: A1