CN111539774A - Method and system for evaluating value of intangible asset, terminal equipment and storage medium - Google Patents

Method and system for evaluating value of intangible asset, terminal equipment and storage medium Download PDF

Info

Publication number
CN111539774A
CN111539774A CN202010370244.4A CN202010370244A CN111539774A CN 111539774 A CN111539774 A CN 111539774A CN 202010370244 A CN202010370244 A CN 202010370244A CN 111539774 A CN111539774 A CN 111539774A
Authority
CN
China
Prior art keywords
data
value evaluation
intangible
intangible asset
model
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
Application number
CN202010370244.4A
Other languages
Chinese (zh)
Inventor
蔡杭
李月
梁议丹
贲流
范力欣
陈天健
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.)
WeBank Co Ltd
Original Assignee
WeBank 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 WeBank Co Ltd filed Critical WeBank Co Ltd
Priority to CN202010370244.4A priority Critical patent/CN111539774A/en
Publication of CN111539774A publication Critical patent/CN111539774A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0278—Product appraisal
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/03—Credit; Loans; Processing thereof

Abstract

The invention discloses a method, a system, terminal equipment and a storage medium for evaluating the value of intangible assets, wherein a central server connected with each data mechanism receives an initial value evaluation result uploaded by each data mechanism and used for evaluating the value of intangible assets to be evaluated, wherein the initial value evaluation result is obtained by inputting target characteristic data of the intangible assets to be evaluated into a value evaluation model obtained based on federal learning training by each data mechanism; and integrating the initial value evaluation results received from the data mechanisms to obtain a comprehensive value evaluation result of the intangible assets to be evaluated. According to the method, under the condition that the data owned by each data organization does not leave the local, namely the privacy and the safety of the data are not influenced, the value of the intangible assets is trained and accurately evaluated by using the value evaluation model, and the efficient development of the intangible asset pledge financing is promoted.

Description

Method and system for evaluating value of intangible asset, terminal equipment and storage medium
Technical Field
The invention relates to the technical field of federal learning, in particular to a method and a system for evaluating the value of intangible assets, terminal equipment and a storage medium.
Background
Due to the fact that the federal learning technology can realize that dispersed small data islands can be combined to be changed into big data analysis through a federal model in a mode of 'data motionless model movement' on the premise of guaranteeing privacy safety of data owned by all participants, application of the federal learning technology in a plurality of technical fields is paid more and more attention.
At present, based on the basic policy that nations strongly encourage intangible asset pledge financing, many enterprises perform financing loan and the like through the intangible assets owned by the pledge so as to provide further operation and development of the enterprises. However, it is often difficult for a loan institution to accurately evaluate the value of intangible assets owned by an enterprise, so that accurate value evaluation for intangible assets is always a difficult problem that is difficult to effectively break through in the process of using intangible assets to carry out pledge financing by the enterprise.
Disclosure of Invention
The invention mainly aims to provide a method, a device, a terminal device and a storage medium for evaluating the value of an intangible asset, aiming at carrying out training and aggregation by utilizing the characteristic data of the intangible asset owned by each dispersed data organization on the premise of protecting the privacy of data based on the federal learning technology so as to accurately evaluate the value of the intangible asset.
In order to achieve the above object, the present invention provides a method for evaluating a value of an intangible asset, wherein the method for evaluating a value of an intangible asset is applied to a central server, the central server is connected with each data organization, and the method for evaluating a value of an intangible asset comprises:
receiving initial value evaluation results uploaded by each data organization and used for evaluating the intangible assets to be evaluated, wherein the initial value evaluation results are obtained by inputting target characteristic data of the intangible assets to be evaluated into a value evaluation model obtained based on federal learning training and predicting by each data organization;
and integrating the initial value evaluation results received from the data mechanisms to obtain a comprehensive value evaluation result of the intangible assets to be evaluated.
Further, the method for evaluating the value of the intangible asset further comprises the following steps:
and recording the contribution degree of each data mechanism to the value evaluation model by combining a block chain technology.
Further, the step of recording the contribution degree of each data organization to the value evaluation model in combination with the blockchain technology includes:
acquiring local training models uploaded by each data organization in the process of obtaining the value evaluation model based on federal learning training;
calculating the contribution degree of each data mechanism to the value evaluation model according to each local training model;
and writing the contribution degree association memory into a preset block chain for recording so that each data mechanism logs in the preset block chain for verification.
In addition, in order to achieve the above object, the present invention further provides a method for evaluating a value of an intangible asset, the method for evaluating a value of an intangible asset is applied to a data organization, the data organization establishes a connection with a central server, and the method for evaluating a value of an intangible asset includes:
extracting target characteristic data of intangible assets to be evaluated;
inputting the target characteristic data into a value evaluation model to obtain an initial value evaluation result for evaluating the value of the intangible asset to be evaluated, wherein the value evaluation model is obtained based on federal learning training;
and uploading the initial value evaluation results to a central server, so that the central server integrates the initial value evaluation results received from the data mechanisms to obtain a comprehensive value evaluation result of the intangible assets to be evaluated.
Further, the step of extracting the target feature data of the intangible asset to be evaluated comprises the following steps:
if the feature data of the intangible asset to be evaluated is locally stored, taking the locally stored feature data as the target feature data, and locally extracting the target feature data;
if the characteristic data of the intangible asset to be evaluated is not stored locally, matching the associated asset of the intangible asset to be evaluated according to the key information of the intangible asset to be evaluated;
and taking the locally stored feature data of the associated assets as the target feature data, and extracting the target feature data from the local.
Further, the method for evaluating the value of the intangible asset further comprises the following steps:
acquiring a federal learning initial model, and locally training the federal learning initial model according to feature sample data of an intangible asset sample to obtain a local training model;
and uploading the local training models to the central server, so that the central server integrates the local training models received from the data mechanisms to obtain the value evaluation model and returns the value evaluation model.
Further, the step of locally training the federal learning initial model according to the feature sample data of the intangible asset sample to obtain a local training model includes:
extracting target feature sample data of each intangible asset sample, wherein the target feature sample data belongs to the feature classes pointed by the federal learning initial model, and the number of the feature classes is greater than or equal to one;
and carrying out local training on the federal learning initial model according to the target feature sample data to obtain a local training model corresponding to the feature class.
Further, the step of uploading the local training models to the central server, so that the central server integrates the local training models received from the data institutions to obtain the first value evaluation model and returning the first value evaluation model includes:
and uploading the local training models to the central server, so that the central server performs iterative training on the local training models with the same feature class in the local training models received from the data mechanisms until convergence, and obtaining and returning value evaluation models corresponding to the feature classes.
In addition, to achieve the above object, the present invention provides a system for evaluating a value of an intangible asset, comprising:
the receiving module is used for receiving initial value evaluation results uploaded by all data organizations and used for carrying out value evaluation on intangible assets to be evaluated, wherein the initial value evaluation results are obtained by inputting target characteristic data of the intangible assets to be evaluated into a value evaluation model obtained based on federal learning training and predicting the target characteristic data of the intangible assets to be evaluated by all the data organizations;
the comprehensive evaluation module is used for integrating the initial value evaluation results received from the data mechanisms to obtain the comprehensive value evaluation result of the intangible asset to be evaluated;
wherein, the value evaluation system of intangible assets further comprises:
the extraction module is used for extracting target characteristic data of the intangible asset to be evaluated;
the initial evaluation module is used for inputting the target characteristic data into a value evaluation model to obtain an initial value evaluation result of the intangible asset to be evaluated, wherein the value evaluation model is obtained based on federal learning training;
and the transmission module is used for uploading the initial value evaluation result to a central server so that the central server can integrate the initial value evaluation results received from the data mechanisms to obtain a comprehensive value evaluation result of the intangible asset to be evaluated.
Further, the system for evaluating the value of the intangible asset further comprises:
and the recording module is used for recording the contribution degree of each data mechanism to the value evaluation model by combining a block chain technology, and distributing the evaluation cost of the value evaluation of the intangible assets to be evaluated to each data mechanism according to the contribution degree.
The functional modules of the value evaluation system of the intangible assets of the invention realize the steps of the value evaluation method of the intangible assets when in operation.
In addition, to achieve the above object, the present invention also provides a terminal device, including: a memory, a processor and a value assessment program for an intangible asset stored on the memory and operable on the processor, the value assessment program for an intangible asset when executed by the processor implementing the steps of the method of assessing the value of an intangible asset as described above.
Further, to achieve the above object, the present invention also provides a storage medium having stored thereon a computer program which, when executed by a processor, realizes the steps of the method for valuing intangible assets as described above.
According to the method, the system, the terminal equipment and the storage medium for evaluating the value of the intangible asset, the initial value evaluation result of evaluating the value of the intangible asset to be evaluated uploaded by each data organization is received, wherein the initial value evaluation result is obtained by inputting the target characteristic data of the intangible asset to be evaluated into a value evaluation model obtained based on federal learning training by each data organization; and integrating the initial value evaluation results received from the data mechanisms to obtain a comprehensive value evaluation result of the intangible assets to be evaluated.
The invention realizes that each data organization establishes a data alliance for evaluating the value of the intangible assets by utilizing the characteristic data of the intangible assets owned by each data organization through the federal learning technology, and trains and utilizes the value evaluation model to accurately evaluate the value of the intangible assets under the condition of ensuring that the data owned by each data organization does not leave the local area in a mode of 'data motionless model movement', namely, no influence on the privacy safety of the data exists, thereby promoting the efficient development of the intangible asset pledge financing.
Drawings
Fig. 1 is a schematic structural diagram of the hardware operation of a terminal device according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram illustrating one embodiment of a method for valuing an intangible asset of the present invention;
FIG. 3 is a schematic flow chart diagram illustrating another embodiment of a method for valuing an intangible asset of the present invention;
FIG. 4 is a flowchart illustrating a detailed process of step S400 in an embodiment of a method for valuating intangible assets of the present invention;
FIG. 5 is a schematic flow chart of an application involved in one embodiment of a method for value assessment of intangible assets of the present invention;
FIG. 6 is a schematic flow chart of another application involved in one embodiment of a method for value assessment of intangible assets of the present invention;
FIG. 7 is a block diagram of a system for valuing intangible assets in accordance with the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a schematic structural diagram of a hardware operating environment related to a terminal device according to an embodiment of the present invention.
It should be noted that fig. 1 is a schematic structural diagram of a hardware operating environment of the terminal device. The terminal equipment of the embodiment of the invention can be terminal equipment such as a PC, a portable computer and the like.
As shown in fig. 1, the terminal device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the terminal device configuration shown in fig. 1 is not intended to be limiting of the terminal device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a distributed task processing program. Among them, the operating system is a program that manages and controls the hardware and software resources of the sample terminal device, a handler that supports distributed tasks, and the execution of other software or programs.
In the terminal apparatus shown in fig. 1, the user interface 1003 is mainly used for data communication with each terminal; the network interface 1004 is mainly used for connecting a background server and performing data communication with the background server; and the processor 1001 may be configured to invoke a value assessment program for intangible assets stored in the memory 1005 and perform the following operations:
receiving initial value evaluation results uploaded by each data organization and used for evaluating the intangible assets to be evaluated, wherein the initial value evaluation results are obtained by inputting target characteristic data of the intangible assets to be evaluated into a value evaluation model obtained based on federal learning training and predicting by each data organization;
and integrating the initial value evaluation results received from the data mechanisms to obtain a comprehensive value evaluation result of the intangible assets to be evaluated.
Further, the processor 1001 may call the value assessment program for intangible assets stored in the memory 1005, and also perform the following operations:
and recording the contribution degree of each data mechanism to the value evaluation model by combining a block chain technology.
Further, the processor 1001 may call the value assessment program for intangible assets stored in the memory 1005, and also perform the following operations:
acquiring local training models uploaded by each data organization in the process of obtaining the value evaluation model based on federal learning training;
calculating the contribution degree of each data mechanism to the value evaluation model according to each local training model;
and writing the contribution degree association memory into a preset block chain for recording so that each data mechanism logs in the preset block chain for verification.
Further, the processor 1001 may call the value assessment program for intangible assets stored in the memory 1005, and also perform the following operations:
extracting target characteristic data of intangible assets to be evaluated;
inputting the target characteristic data into a value evaluation model to obtain an initial value evaluation result for evaluating the value of the intangible asset to be evaluated, wherein the value evaluation model is obtained based on federal learning training;
and uploading the initial value evaluation results to a central server, so that the central server integrates the initial value evaluation results received from the data mechanisms to obtain a comprehensive value evaluation result of the intangible assets to be evaluated.
Further, the processor 1001 may call the value assessment program for intangible assets stored in the memory 1005, and also perform the following operations:
if the feature data of the intangible asset to be evaluated is locally stored, taking the locally stored feature data as the target feature data, and locally extracting the target feature data;
if the characteristic data of the intangible asset to be evaluated is not stored locally, matching the associated asset of the intangible asset to be evaluated according to the key information of the intangible asset to be evaluated;
and taking the locally stored feature data of the associated assets as the target feature data, and extracting the target feature data from the local.
Further, the processor 1001 may call the value assessment program for intangible assets stored in the memory 1005, and also perform the following operations:
acquiring a federal learning initial model, and locally training the federal learning initial model according to feature sample data of an intangible asset sample to obtain a local training model;
and uploading the local training models to the central server, so that the central server integrates the local training models received from the data mechanisms to obtain the value evaluation model and returns the value evaluation model.
Further, the processor 1001 may call the value assessment program for intangible assets stored in the memory 1005, and also perform the following operations:
extracting target feature sample data of each intangible asset sample, wherein the target feature sample data belongs to the feature classes pointed by the federal learning initial model, and the number of the feature classes is greater than or equal to one;
and carrying out local training on the federal learning initial model according to the target feature sample data to obtain a local training model corresponding to the feature class.
Further, the processor 1001 may call the value assessment program for intangible assets stored in the memory 1005, and also perform the following operations:
and uploading the local training models to the central server, so that the central server performs iterative training on the local training models with the same feature class in the local training models received from the data mechanisms until convergence, and obtaining and returning value evaluation models corresponding to the feature classes.
Based on the above structure, various embodiments of the method for evaluating the value of an intangible asset of the present invention are presented.
Referring to fig. 2, fig. 2 is a schematic flow chart of a value evaluation method for intangible assets according to a first embodiment of the present invention.
While a logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in an order different than presented herein.
The method for evaluating the value of intangible assets in the embodiment of the present invention is applied to the terminal device, and the terminal device in the embodiment of the present invention may be a terminal device such as a PC, a portable computer, or the like, and is not limited specifically herein.
The method for evaluating the value of the intangible asset is applied to a central server, the central server is connected with each data mechanism, and the method for evaluating the value of the intangible asset comprises the following steps:
and S100, receiving initial value evaluation results uploaded by each data organization and used for evaluating the intangible assets to be evaluated, wherein the initial value evaluation results are obtained by inputting target characteristic data of the intangible assets to be evaluated into a value evaluation model obtained based on federal learning training by each data organization and predicting.
It should be noted that, in this embodiment, data unions that each have a certain feature data of an intangible asset are established in advance through a federal learning technology, a value evaluation model is obtained through joint training of the feature data that each own, and the data unions that perform value evaluation on the intangible asset are obtained through the value evaluation model, in the data unions established based on the federal learning technology, each data unions negotiate with participant identities to obtain a central server as a coordinator of federal learning, and the central server may be a server or a service platform provided by any third-party service provider.
In the data alliance established based on the federal learning technology, each data agency respectively extracts target characteristic data of each intangible asset to be evaluated, the target characteristic data is input into a value evaluation model obtained by training characteristic sample data of intangible asset samples provided by each data agency in the data alliance which is used by federal learning in advance, so that each initial value evaluation result of the intangible asset to be evaluated is obtained by predicting the value evaluation model, and then each initial value evaluation result uploaded by each data agency is received by a central server in the data alliance.
Further, in another embodiment, if the central server already owns the target feature data of the intangible asset to be evaluated, the central server may directly input the target feature data into the first value evaluation model at the home terminal, so as to directly train at the home terminal to obtain an intermediate result of value evaluation for the intangible asset to be evaluated.
And S200, integrating the initial value evaluation results received from the data mechanisms to obtain the comprehensive value evaluation result of the intangible assets to be evaluated.
After receiving each initial value evaluation result of the intangible asset to be evaluated from each connected data mechanism, the central server comprehensively evaluates each initial value evaluation result according to the characteristic weight of each target characteristic data of the intangible asset to be evaluated aiming at the intangible asset value, thereby obtaining the comprehensive value evaluation result of the intangible asset to be evaluated.
In this embodiment, the target feature data of the intangible asset to be evaluated includes, but is not limited to, transaction data, pledge data, litigation data, and validity period of the intangible asset to be evaluated, and the feature weight of the target feature data for the value of the intangible asset may be defined by negotiation of each data organization in a specific application, for example, the feature weights of the transaction data, pledge data, litigation data, and validity period for the value of the intangible asset are respectively: 20%, 30% and 30%, it should be understood that in other embodiments, the target feature data of the intangible asset to be evaluated may also include other types of feature data, and the feature weight of each target feature data for the intangible asset value may also be defined as other values different from those listed above.
Specifically, for example, (for convenience of presentation and understanding, the following description will be made with respect to specific examples of intangible assets in terms of intellectual property rights, it should be understood that the method for evaluating value of intangible assets of the present invention is of course equally applicable to any other types of identifiable non-monetary assets owned or controlled by enterprises or individuals, without physical forms) in each patent transaction center which owns intellectual property rights to be evaluated-patent 1 transaction data, the transaction data of each owned patent 1 is input into a value evaluation model, thereby each initial value evaluation result of patent 1 predicted based on the transaction data is obtained, and then each initial value evaluation result is uploaded to a central server, and other financial institutions and law firms which own the mortgage data and litigation data of patent 1, respectively, are obtained based on the mortgage data, the non-monetary assets, and the like in the same manner as described above, The litigation data and the effective age prediction obtain each initial value evaluation result of the patent 1 and upload the initial value evaluation result to the central server.
After receiving the initial value evaluation results of the patent 1, the central server performs weighted average on the initial value evaluation results predicted based on the transaction data to integrate an initial value evaluation result predicted based on the transaction data, similarly performs weighted average on the initial value evaluation results predicted based on the pledge data, litigation data and effective age to integrate an initial value evaluation result predicted based on the pledge data, an initial value evaluation result predicted based on the litigation data and an initial value evaluation result predicted based on the effective age, and then multiplies the initial value evaluation results predicted based on the transaction data, the pledge data, the litigation data and the effective age by the transaction data, the pledge data and the initial value evaluation results predicted based on the effective age by the central server, Litigation data and feature weights of effective age against intangible asset value: 20%, 30% and 30%, thereby giving the comprehensive value evaluation results of this patent 1.
Further, in an embodiment, the method for evaluating the value of the intangible asset of the present invention may further include:
step S300, recording the contribution of each data organization to the value evaluation model by combining a block chain technique.
In the data alliance established based on the federal learning technology, the central server is combined with a block chain technology, the contribution degree of each data organization aiming at the value evaluation model in the process of obtaining the value evaluation model based on the federal learning training is recorded in the block chain taking each data organization as a pivot, so that after the comprehensive value evaluation result of the intangible asset to be evaluated is obtained, the evaluation cost collected by evaluating the value of the intangible asset to be evaluated is distributed to each data organization according to the contribution degree recorded in the block chain.
Further, step S300 may include:
step S301, acquiring local training models uploaded by each data organization in the process of obtaining the value evaluation model based on federal learning training;
in the data alliance established based on the federal learning technology, in the process of obtaining a value evaluation model based on the federal learning training, a central server obtains sample characteristic data of intangible asset samples owned by each data organization, and local training is carried out on the initial model of the federal learning, so that a local training model is obtained.
It should be noted that, in this embodiment, after each data mechanism performs local training on the joint learning initial model by using sample feature data of an intangible asset sample owned by each data mechanism, so as to obtain a local training model, the local training model is uploaded to the central server for iterative training, so as to implement a training mode of "data motionless model movement", and ensure privacy and security of data owned by each data mechanism.
Step S302, calculating the contribution degree of each data mechanism to the value evaluation model according to each local training model;
after the central server acquires the local training models of the data organizations, the local training models of the data organizations are respectively compared with the federal learning initial model, so that the performance improvement degrees of the local training models of the data organizations compared with the federal learning initial model are calculated, and the performance improvement degrees of the models are converted into the contribution degrees of the data organizations on the value evaluation model obtained by integrating the local training models.
It should be noted that, in this embodiment, in the process that the central server calculates the degree of performance improvement of each local training model of each data organization compared with each model between the federal learning initial models, the specific calculation manner adopted by the central server, and the degree of performance improvement of each model by the central server are converted into the contribution degree of each data organization to the value evaluation model obtained by integrating the local training models, the specific conversion manner adopted by the central server may be any mature calculation manner.
Step S303, writing the contribution degree association memory into a preset block chain for recording, so that each data mechanism logs in the preset block chain for verification.
The central server is combined with a block chain technology in advance, a preset block chain is established by taking each connected data mechanism as a pivot, and after each contribution degree of each data mechanism aiming at the first price evaluation model is obtained through calculation, the central server correspondingly associates each contribution degree with each data mechanism and writes the contribution degrees in the preset block chain so that each data mechanism serving as the pivot of the preset block chain can be logged in at any time for inquiry and authentication.
In this embodiment, in the data federation established based on the federal learning technology, each data agency respectively extracts target feature data of each owned intangible asset to be evaluated, and inputs the target feature data into a value evaluation model obtained by training feature sample data of intangible asset samples provided by each data agency in the data federation which has been used in advance through the federal learning, so as to obtain each initial value evaluation result for evaluating the value of the intangible asset to be evaluated by predicting through the first value evaluation model, and then a central server in the data federation receives each initial value evaluation result uploaded by each data agency respectively; after receiving each initial value evaluation result of the intangible asset to be evaluated from each connected data mechanism, the central server comprehensively evaluates each initial value evaluation result according to the characteristic weight of each target characteristic data of the intangible asset to be evaluated aiming at the intangible asset value, thereby obtaining the comprehensive value evaluation result of the intangible asset to be evaluated.
In addition, in the data alliance established based on the federal learning technology, the central server combines the block chain technology, records the contribution degree of each data organization aiming at the value evaluation model in the process of obtaining the value evaluation model based on the federal learning training in the block chain taking each data organization as a pivot, and distributes the evaluation cost collected by evaluating the value of the intangible asset to be evaluated to each data organization according to the contribution degree recorded in the block chain after obtaining the comprehensive value evaluation result of the intangible asset to be evaluated.
The method has the advantages that the data alliance for evaluating the value of the intangible assets is established by establishing each data organization through the federal learning technology and utilizing the characteristic data of the intangible assets owned by each data organization, and under the condition that the data owned by each data organization does not leave the local area, namely, no influence on the privacy safety of the data exists, the value of the intangible assets is accurately evaluated by training and utilizing the value evaluation model, so that the efficient development of the intangible asset pledge financing is promoted; in addition, the contribution degree of the value evaluation model is obtained by combining the blockchain technology and aiming at the federal learning training of each data organization, so that the evaluation prediction process of the intangible assets to be evaluated by each data organization serving as each pivot of the blockchain can be conveniently inquired and authenticated, the evaluation cost of the intangible assets can be more clearly recorded according to the contribution degree, and the efficiency of evaluating the value of the intangible assets is improved.
Further, a second embodiment of the method for evaluating the value of an intangible asset of the present invention is provided, referring to fig. 3, fig. 3 is a schematic flow chart of the second embodiment of the method for evaluating the value of an intangible asset of the present invention, and in the second embodiment of the method for evaluating the value of an intangible asset of the present invention, the method for evaluating the value of an intangible asset of the present invention is applied to a data mechanism, and the data mechanism is connected with a central server, and the method for evaluating the value of an intangible asset of the present invention comprises:
and S400, extracting target characteristic data of the intangible asset to be evaluated.
In the data alliance established based on the federal learning technology, after a value evaluation model is obtained by each data organization based on the federal learning training, target feature data of intangible assets to be evaluated are extracted from feature data of the intangible assets owned locally.
Further, referring to fig. 4, fig. 4 shows a detailed flow of step S400 in the present embodiment, where the step S400 may include:
step S401, if the feature data of the intangible asset to be evaluated is locally stored, the locally stored feature data is used as the target feature data, and the target feature data is locally extracted;
in the data alliance established based on the federal learning technology, after a first price evaluation model is obtained by each data organization based on the federal learning training, if the feature data of the intangible asset to be evaluated is detected to include the feature data of the intangible asset to be evaluated, the feature data of the intangible asset to be evaluated is used as target feature data, and the target feature data is extracted from the local.
Specifically, for example, the current data organization is any one of the transaction centers owning the transaction data of the intellectual property right to be evaluated-patent 1, as shown in the application flow of fig. 7, the central server performs the value evaluation operation of the intellectual property right to be evaluated-patent 1 in the belonging block chain, after the central server receives the document of the patent 1, any one of the information identifying the patent 1 is transmitted to each data organization for matching the target feature data of the patent 1, that is, after the current data organization receives the information identifying the patent 1, whether the transaction data of the patent 1 is included in all the transaction data stored locally is detected by the current data organization, if yes, the transaction data is directly taken as one of the target feature data (i.e. the target transaction data) of the patent 1 and extracted, and similarly, the other data organizations such as each financial organization owning the pledge data, Each law firm with litigation data locally extracts other target feature data (i.e., target pledge data, target litigation data) of the patent 1 in the same manner as described above.
Step S402, if the characteristic data of the intangible asset to be evaluated is not stored locally, matching the associated asset of the intangible asset to be evaluated according to the key information of the intangible asset to be evaluated;
in the data alliance established based on the federal learning technology, after a first price evaluation model is obtained by each data organization based on the federal learning training, if the feature data of the intangible assets stored locally is detected to be free from the feature data of the intangible assets to be evaluated, the key information of the intangible assets to be evaluated is extracted, and then the associated assets with the key information of which the similarity reaches a preset threshold value are matched.
It should be noted that, in this embodiment, the preset threshold may be specifically and autonomously defined in practical application based on needs, and the method for evaluating the value of the intangible asset of the present invention does not specifically limit the specific expression form, the numerical value, and the like of the preset threshold.
Specifically, for example, the current data organization is any one of the transaction centers that possess the transaction data of the intellectual property right to be evaluated-patent 1, as shown in the application flow of fig. 6, after the central server receives the document of the intellectual property right to be evaluated-patent 1 that needs to be evaluated, any one of the information identifying the patent 1 is transmitted to each data organization to match the target feature data of the patent 1, after the current data organization receives the information identifying the patent 1, it is detected whether the transaction data of the patent 1 is included in all the transaction data stored locally, if not, the central server extracts the key information (such as the theme and each keyword, etc.) of the document of the patent 1 by using the existing mature key information extraction technology, such as the "theme extraction model" in the natural language processing technology, and sets the corresponding weight value, and then matching the key information with patent documents in a patent basic document database (or a cloud service platform and the like) to search out other candidate patent documents similar to the patent 1, and extracting one or more candidate documents of which the similarity with the patent 1 is greater than or equal to a preset threshold value from the candidate patent documents according to the sequence of the similarity between the candidate patent documents and the patent 1 to serve as associated assets of the patent 1 and feed the associated assets back to a central server.
Step S403, using the locally stored feature data of the associated asset as the target feature data, and extracting the target feature data from the local.
And after the central server is matched to obtain the associated assets with high similarity to the intangible assets to be evaluated, each data mechanism takes the feature data of the associated assets as target feature data and extracts the target feature data from the locally stored feature data of the intangible assets.
Specifically, for example, as shown in the application flow of fig. 6, after the central server receives the document of the associated asset with high similarity to the intellectual property right-patent 1 to be evaluated, which is obtained through document similarity matching, any one of the information identifying the associated asset is transmitted to each data organization to match the target feature data of the associated asset, that is, after the current trading center receives the information identifying the associated asset, whether the transaction data of the associated asset is included in all the transaction data stored locally is detected, if yes, the transaction data is directly taken as one of the target feature data (i.e., the target transaction data) of the associated asset and extracted, similarly, the other data organizations, such as financial institutions having the pledge data and law firms having the litigation data, extract other target feature data (i.e., the target pledge data) of the associated asset locally in the same manner as described above, Target litigation data).
Step S500, inputting the target characteristic data into a value evaluation model to obtain an initial value evaluation result for evaluating the value of the intangible asset to be evaluated, wherein the value evaluation model is obtained based on federal learning training;
after extracting target characteristic data of the intangible assets to be evaluated from local by each data organization, inputting the target characteristic data into a value evaluation model obtained by training the characteristic sample data of the intangible asset sample provided by each data organization in the data alliance through federal learning in advance, and thus obtaining each initial value evaluation result for evaluating the value of the intangible assets to be evaluated by training the characteristic sample data by the value evaluation model.
Step S600, uploading the initial value evaluation results to a central server, so that the central server integrates the initial value evaluation results received from the data mechanisms, and a comprehensive value evaluation result of the intangible assets to be evaluated is obtained.
Each data organization inputs each initial value evaluation result predicted by a first price evaluation model by using target characteristic data of the intangible asset to be evaluated extracted from local, and uploads the initial value evaluation result to a central server in a data alliance established based on federal learning, and the central server receives each initial value evaluation result uploaded by each data organization respectively to carry out comprehensive evaluation, so that the comprehensive value evaluation result of the intangible asset to be evaluated is obtained.
Specifically, for example, in the application flow shown in fig. 6, after each patent transaction center having the intellectual property-patent 1 transaction data to be evaluated inputs the transaction data of the respective patent 1 into the value evaluation model to obtain each initial value evaluation result of the patent 1 predicted based on the transaction data, each initial value evaluation result is uploaded to the center server, and each financial institution and law firm having the patent 1 pledge data and litigation data, respectively, obtains each initial value evaluation result of the patent 1 based on the pledge data, the litigation data and the effective age prediction in the same manner as above and uploads the initial value evaluation results to the center server.
After receiving the initial value evaluation results of the patent 1, the central server performs weighted average on the intermediate results predicted based on the transaction data to integrate an initial value evaluation result predicted based on the transaction data, and similarly performs weighted average on the intermediate results predicted by the pledge data, the litigation data and the effective age to integrate an initial value evaluation result predicted based on the pledge data, and an initial value evaluation result predicted based on litigation data, and an initial value evaluation result predicted based on the validity period, and then, the central server will predict the intermediate results based on the transaction data, pledge data, litigation data and effective age, and correspondingly multiplying the transaction data, the pledge data, the litigation data and the characteristic weight of the effective age to the intangible asset value: 20%, 30% and 30%, thereby obtaining the results of the comprehensive value evaluation of this patent 1.
In the embodiment, in the data alliance established based on the federal learning technology, after each data organization obtains a value evaluation model based on the federal learning training, target feature data of intangible assets to be evaluated are extracted from feature data of the intangible assets owned locally; inputting the target characteristic data into a value evaluation model obtained by training characteristic sample data of intangible asset samples provided by each data organization in the data alliance which is used by federal learning in advance, so as to obtain each initial value evaluation result of the intangible asset to be evaluated through prediction of the value evaluation model; and then uploading each initial value evaluation result to a central server in a data alliance established based on federal learning, and performing comprehensive evaluation by receiving each initial value evaluation result uploaded by each data agency by the central server, so as to obtain a comprehensive value evaluation result of the intangible asset to be evaluated.
The method and the system realize that a data alliance for evaluating the value of the intangible assets is established by each data organization through the federal learning technology by utilizing the characteristic data of the intangible assets owned by each data organization, and the value of the intangible assets is accurately evaluated by utilizing a value evaluation model obtained based on federal learning training in a public transparent block chain in a mode of a data immobility model under the condition of ensuring that the data owned by each data organization does not leave the local area, namely, no influence on the privacy safety of the data exists, so that the efficient development of the intangible asset pledge financing is promoted.
Further, a third embodiment of the method for valuing an intangible asset of the present invention is proposed based on the second embodiment of the method for valuing an intangible asset described above. In a third embodiment of the method for valuing an intangible asset of the present invention, the method for valuing an intangible asset of the present invention may further comprise:
step S700, obtaining a federal learning initial model, and carrying out local training on the federal learning initial model according to feature sample data of an intangible asset sample to obtain a local training model;
it should be noted that, in this embodiment, the federal learning initial model may be a federal learning initial model that is generated by a central server and sequentially issued to each data agency in a data federation that is established based on a federal learning technology and used for performing value evaluation on intangible assets, and is used for performing iterative training to obtain the federal learning initial model of the value evaluation model, or may be a federal learning initial model that is generated by each data agency itself at the local terminal based on feature sample data of intangible asset samples owned by each data agency itself and used for performing iterative training to obtain the value evaluation model.
In the data alliance established based on the federal learning technology, each data organization obtains a federal learning initial model used for iterative training to obtain a value evaluation model, and then local training is carried out on each local end by using characteristic sample data of an intangible asset sample, so that each local training model is obtained.
Step S800, uploading the local training models to the central server, so that the central server integrates the local training models received from the data mechanisms to obtain the value evaluation model and returning the value evaluation model.
And each data organization locally trains by using the characteristic sample data of the owned intangible asset sample at the home terminal, so that each obtained local training model is uploaded to a central server in the data alliance, and the central server integrates each received local model uploaded by each data organization, so that a first price evaluation model for performing value prediction and evaluation on the intangible asset is obtained and returned to each data organization.
It should be noted that, in this embodiment, the local training model uploaded to the central server by each data organization may specifically be: and each data mechanism trains the sample characteristic data of the input intangible asset sample based on the federal learning initial model at the home terminal to obtain parameters such as each model index, factor and the like of the local training model.
Further, in an embodiment, in the step S700, the step of locally training the federal learning initial model according to the feature sample data of the intangible asset sample to obtain a local training model may include:
step S701, extracting target feature sample data of each intangible asset sample, wherein the target feature sample data belongs to the feature classes pointed by the federal learning initial model, and the number of the feature classes is greater than or equal to one;
step S702, local training is carried out on the federal learning initial model according to the target feature sample data to obtain a local training model corresponding to the feature type.
It should be noted that, in this example, the federal learning initial model may be specifically a horizontal federal learning initial model, and the feature categories pointed to by the horizontal federal learning initial model include, but are not limited to, transaction data, pledge data, and litigation data.
In the data alliance established based on the federal learning technology, the central server sends each horizontal federal learning initial model to a corresponding data organization according to transaction data, pledge data and litigation data which are respectively pointed by each horizontal federal learning initial model generated in advance, after each data organization obtains the horizontal federal learning initial model, according to the transaction data, the pledge data and the litigation data which are pointed by the horizontal federal learning initial model, from the feature sample data of the intangible asset sample stored locally, extracting target transaction sample data, target pledge sample data and target litigation sample data, and locally training each horizontal federal learning initial model so as to obtain each federal trading model, each federal pledge model and each federal litigation model corresponding to the trading data, the pledge data and the litigation data.
Specifically, for example, as shown in the application flow of fig. 5, a data federation established based on the federal learning technology also performs an iterative training process on a first value evaluation model in a belonging block chain, a central server in the data federation generates a horizontal federal learning initial model for performing iterative training on transaction data, pledge data and litigation data based on intangible assets-intellectual property, respectively, and then issues the horizontal federal learning initial model pointing to the transaction data to transaction centers such as the trading institutions 1 and 2 in the current data federation, and similarly, issues the horizontal federal learning initial model pointing to the pledge data and the litigation data to financial institutions such as the pledge institution 1 and the pledge 2 in the current data federation, and law firms such as the litigation institution 1 and the litigation institution 2.
After the transaction centers of the transaction institutions 1, the transaction institutions 2 and the like acquire the transverse federal learning initial model pointing to the transaction data, the transaction data of intellectual property rights stored locally is used as training sample data, the transverse federal learning initial model is trained locally to obtain local training models obtained by performing local training on the basis of the transaction data, and similarly, the financial institutions of the pledge institutions 1, the pledge institutions 2 and the like and law firms of the litigation institutions 1, the litigation institutions 2 and the like perform local training on the basis of the locally stored data respectively to correspondingly obtain local training models obtained by performing local training on the basis of the pledge data and local training models obtained by performing local training on the basis of the litigation data.
Further, the step S800 may include:
step S800, uploading the local training models to the central server, so that the central server performs iterative training on each local training model with the same feature type among the local training models received from each data mechanism until convergence, and obtains and returns a value evaluation model corresponding to each feature type.
Specifically, for example, each transaction center such as the transaction institution 1 and the transaction institution 2 uploads a local training model obtained by local training based on transaction data and obtained by local training to a central server, the central server receives the local training models and performs weighted average processing on the local training models to integrate the local training models into a to-be-selected federal transaction model, and when the central server detects that the to-be-selected federal transaction model is in gradient convergence, the to-be-selected federal transaction model is determined to be one of the value evaluation models (namely, the federal transaction models) which finally perform initial value evaluation on intellectual property rights to be evaluated based on the transaction data, and then the value evaluation model is returned to each transaction center such as the transaction institution 1 and the transaction institution 2 again for performing initial value evaluation prediction on the subsequent intellectual property rights to be evaluated, when the central server detects that the gradient of the to-be-evaluated federal transaction model is not converged, the model is issued to each transaction center such as each transaction organization 1 and each transaction organization 2 again for iterative training until the gradient convergence of the to-be-evaluated federal transaction model is detected, and similarly, the central server obtains other types of value evaluation models (namely, a federal pledge model and a federal litigation model) for performing initial value evaluation on intellectual property rights to be evaluated based on the above mode, and then the value evaluation models are correspondingly returned to each financial institution such as the pledge organization 1 and the pledge organization 2 and each law firm such as the litigation organization 1 and the litigation organization 2 again for performing initial value evaluation prediction on the following intellectual property rights to be evaluated.
Further, in another embodiment, the central server may further send the detected gradient-converged federal transaction model, federal pledge model and federal litigation model to the corresponding data organizations again, so that after sample characteristic data of intangible asset samples stored locally by the data organizations are updated, the updated data are continuously used for performing iterative training on the federal transaction model, the federal pledge model or the federal litigation model locally, thereby improving the prediction accuracy of the model and further ensuring the accuracy of value evaluation on intangible assets.
Further, in another embodiment, the federal learning initial model further includes: in the step S700, the step of performing local training on the federal learning initial model according to the feature sample data of the intangible asset sample to obtain a local training model may further include:
step A, detecting target intangible asset samples pointed by the longitudinal federal learning initial model, wherein the number of the target intangible asset samples is greater than or equal to one;
and B, extracting the feature sample data of the target intangible assets from the local, and performing local training on the longitudinal federal learning initial model according to the feature sample data of each target intangible asset to obtain a local training model.
In the data alliance established based on the federal learning technology, a central server generates a longitudinal federal learning initial model in advance according to transaction data, pledge data and litigation data of intangible assets, then the longitudinal federal learning initial model is issued to all data agencies in the affiliated data alliance, each data agency aims at the received longitudinal federal learning initial model, during each iterative training process performed by the central server based on the longitudinal federal learning initial model, detecting the target intangible asset sample pointed by the longitudinal federal learning initial model for sample alignment, and then, detecting the target intangible asset sample by each data mechanism from the own intangible asset sample, locally extracting the characteristic sample data of the target intangible asset sample, and locally training the longitudinal federal learning initial model to obtain a local training model.
Specifically, for example, a central server in a data federation established based on the federal learning technology generates a vertical federal learning initial model for iterative training based on transaction data, pledge data and litigation data of intangible assets-intellectual property rights, then specifies one or more target intellectual property right samples in each iterative training process for the vertical federal learning initial model, and issues the vertical federal learning initial model to each transaction center, each financial institution and each law firm in the current data federation.
After each transaction center, each financial institution and each lawyer affair place acquire the longitudinal federal learning initial model, the target intellectual property sample is detected from the intellectual property stored locally, transaction sample data, pledge sample data and litigation sample data of the target intellectual property sample are extracted, and the longitudinal federal learning initial model is trained locally by the transaction sample data, pledge sample data and litigation sample data, so that each local training model is obtained.
Further, the step S800 may further include:
and step S800, uploading the local training models to the central server, so that the central server can perform iterative training on the local training models received from the data mechanisms until convergence, and then the value evaluation model is obtained and returned.
Specifically, for example, each transaction center, each financial institution, and each law firm uploads transaction sample data, pledge sample data, and litigation sample data, which are obtained by local training and are based on a target intellectual property sample, to a center server, the center server receives the local training models and performs weighted average processing on the local training models to integrate the local training models into a candidate value evaluation model for initial value evaluation of intellectual property rights, and when the center server detects gradient convergence of the candidate value evaluation model, the candidate value evaluation model is determined as a value evaluation model for final initial value evaluation of intellectual property rights based on the transaction data, pledge data, and litigation data, and then the value evaluation model is returned to each transaction center, And each financial institution and each law firm, or when the central server detects that the gradient of the value evaluation model to be selected is not converged, appointing the target intellectual property sample again and sending the model to each transaction center, each financial institution and each lawyer affair so as to carry out iterative training until the gradient of the value evaluation model to be selected is converged.
In this embodiment, in the data federation established based on the federal learning technology, each data agency acquires a federal learning initial model for iterative training to obtain a value evaluation model, and then performs local training on each local terminal by using feature sample data of an existing intangible asset sample to obtain each local training model; and each data organization locally trains by using the characteristic sample data of the owned intangible asset sample at each home terminal, so that each obtained local training model is uploaded to a central server in the data alliance, and the central server integrates each received local model uploaded by each data organization, so that a value evaluation model for performing value prediction evaluation on the intangible asset is obtained.
The method and the system realize that a data alliance for evaluating the value of the intangible assets is established by establishing each data organization through the federal learning technology and utilizing the characteristic data of the intangible assets owned by each data organization, and a value evaluation model for evaluating the initial value of the intangible assets is obtained by training in a mode of a data immobility model under the condition of ensuring that the data owned by each data organization does not leave the local, namely, no influence on the privacy safety of the data exists, so that the accuracy of evaluating the value of the intangible assets and the evaluation efficiency of the value of the intangible assets are improved.
In addition, referring to fig. 7, an embodiment of the present invention further provides a system for evaluating a value of an intangible asset, where the system for evaluating a value of an intangible asset includes:
the receiving module is used for receiving initial value evaluation results uploaded by all data organizations and used for carrying out value evaluation on intangible assets to be evaluated, wherein the initial value evaluation results are obtained by inputting target characteristic data of the intangible assets to be evaluated into a value evaluation model obtained based on federal learning training and predicting the target characteristic data of the intangible assets to be evaluated by all the data organizations;
and the comprehensive evaluation module is used for integrating the initial value evaluation results received from the data organizations to obtain the comprehensive value evaluation result of the intangible assets to be evaluated.
Preferably, the system for evaluating the value of an intangible asset of the present invention further comprises:
and the recording module is used for recording the contribution degree of each data mechanism to the value evaluation model by combining a block chain technology, and distributing the evaluation cost of the value evaluation of the intangible assets to be evaluated to each data mechanism according to the contribution degree.
Preferably, the recording module comprises:
the acquisition unit is used for acquiring each local training model uploaded by each data organization in the process of obtaining the value evaluation model based on federal learning training;
the calculation unit is used for calculating the contribution degree of each data mechanism to the value evaluation model according to each local training model;
and the recording unit is used for writing the contribution degree association memory into a preset block chain for recording so as to log in the preset block chain for verification by each data mechanism.
Preferably, the system for evaluating the value of an intangible asset of the present invention further comprises:
the extraction module is used for extracting target characteristic data of the intangible asset to be evaluated;
the initial evaluation module is used for inputting the target characteristic data into a value evaluation model to obtain an initial value evaluation result of the intangible asset to be evaluated, wherein the value evaluation model is obtained based on federal learning training;
and the transmission module is used for uploading the initial value evaluation result to a central server so that the central server can integrate the initial value evaluation results received from the data mechanisms to obtain a comprehensive value evaluation result of the intangible asset to be evaluated.
Preferably, the extraction module comprises:
the first extraction unit is used for taking the locally stored characteristic data as the target characteristic data and extracting the target characteristic data from the local area if the characteristic data of the intangible asset to be evaluated is locally stored;
the matching unit is used for matching the associated assets of the intangible assets to be evaluated according to the key information of the intangible assets to be evaluated if the characteristic data of the intangible assets to be evaluated is not stored locally;
and the second extraction unit is used for taking the locally stored feature data of the associated assets as the target feature data and extracting the target feature data from the local.
Preferably, the system for evaluating the value of an intangible asset of the present invention further comprises:
the training module is used for obtaining a federal learning initial model and carrying out local training on the federal learning initial model according to the characteristic sample data of the intangible asset sample to obtain a local training model;
and the integration module is used for uploading the local training models to the central server so that the central server integrates the local training models received from the data mechanisms to obtain the value evaluation model and returns the value evaluation model.
Preferably, the training module comprises:
a third extraction unit, configured to extract target feature sample data of each intangible asset sample, where the target feature sample data belongs to a feature class pointed by the federal learning initial model, and the number of the feature classes is greater than or equal to one;
and the training unit is used for carrying out local training on the federal learning initial model according to the target feature sample data to obtain a local training model corresponding to the feature class.
Preferably, the integration module comprises:
and the integration unit is used for uploading the local training models to the central server so that the central server can perform iterative training on the local training models with the same characteristic class in the local training models received from the data mechanisms until convergence, and obtain and return value evaluation models corresponding to the characteristic classes.
The steps implemented by the functional modules of the device for evaluating the value of an intangible asset of the present invention during operation can refer to the second embodiment and the third embodiment of the method for evaluating the value of an intangible asset of the present invention, and are not described herein again.
In addition, an embodiment of the present invention further provides a terminal device, where the terminal device includes: a memory, a processor, and a value assessment program for an intangible asset stored on the memory and executable on the processor, the value assessment program for an intangible asset when executed by the processor implementing the steps of the method for assessing the value of an intangible asset as described above.
The steps implemented when the value evaluation program of the intangible asset running on the processor is executed may refer to various embodiments of the value evaluation method of the intangible asset of the present invention, and are not described herein again.
In addition, the embodiment of the present invention further provides a storage medium applied to a computer, where the storage medium may be a non-volatile computer-readable storage medium, and the storage medium stores a value evaluation program of an intangible asset, and the value evaluation program of the intangible asset implements the steps of the method for evaluating the value of the intangible asset when executed by a processor.
The steps implemented when the value evaluation program of the intangible asset running on the processor is executed may refer to various embodiments of the value evaluation method of the intangible asset of the present invention, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (12)

1. A method for evaluating the value of an intangible asset is applied to a central server, the central server is connected with each data mechanism, and the method for evaluating the value of the intangible asset comprises the following steps:
receiving initial value evaluation results uploaded by each data organization and used for evaluating the intangible assets to be evaluated, wherein the initial value evaluation results are obtained by inputting target characteristic data of the intangible assets to be evaluated into a value evaluation model obtained based on federal learning training and predicting by each data organization;
and integrating the initial value evaluation results received from the data mechanisms to obtain a comprehensive value evaluation result of the intangible assets to be evaluated.
2. The method for valuing an intangible asset of claim 1, wherein the method for valuing an intangible asset further comprises:
and recording the contribution degree of each data mechanism to the value evaluation model by combining a block chain technology.
3. The method of valuing an intangible asset of claim 2, wherein the step of recording the contribution of each of the data institutions to the valuation model in conjunction with blockchain techniques comprises:
acquiring local training models uploaded by each data organization in the process of obtaining the value evaluation model based on federal learning training;
calculating the contribution degree of each data mechanism to the value evaluation model according to each local training model;
and writing the contribution degree association memory into a preset block chain for recording so that each data mechanism logs in the preset block chain for verification.
4. A method for evaluating the value of an intangible asset is applied to a data mechanism, the data mechanism is connected with a central server, and the method for evaluating the value of the intangible asset comprises the following steps:
extracting target characteristic data of intangible assets to be evaluated;
inputting the target characteristic data into a value evaluation model to obtain an initial value evaluation result for evaluating the value of the intangible asset to be evaluated, wherein the value evaluation model is obtained based on federal learning training;
and uploading the initial value evaluation results to a central server, so that the central server integrates the initial value evaluation results received from the data mechanisms to obtain a comprehensive value evaluation result of the intangible assets to be evaluated.
5. The method for valuing an intangible asset of claim 4, wherein the step of extracting target feature data of the intangible asset to be assessed comprises:
if the feature data of the intangible asset to be evaluated is locally stored, taking the locally stored feature data as the target feature data, and locally extracting the target feature data;
if the characteristic data of the intangible asset to be evaluated is not stored locally, matching the associated asset of the intangible asset to be evaluated according to the key information of the intangible asset to be evaluated;
and taking the locally stored feature data of the associated assets as the target feature data, and extracting the target feature data from the local.
6. The method for valuing an intangible asset of claim 4, wherein the method for valuing an intangible asset further comprises:
acquiring a federal learning initial model, and locally training the federal learning initial model according to feature sample data of an intangible asset sample to obtain a local training model;
and uploading the local training models to the central server, so that the central server integrates the local training models received from the data mechanisms to obtain the value evaluation model and returns the value evaluation model.
7. The method for valuing an intangible asset of claim 6, wherein the step of locally training the federal learning initial model according to the feature sample data of the intangible asset sample to obtain a local training model comprises:
extracting target feature sample data of each intangible asset sample, wherein the target feature sample data belongs to the feature classes pointed by the federal learning initial model, and the number of the feature classes is greater than or equal to one;
and carrying out local training on the federal learning initial model according to the target feature sample data to obtain a local training model corresponding to the feature class.
8. The method of valuing an intangible asset of claim 6, wherein the step of uploading the local training models to the central server for the central server to integrate the local training models received from the data institutions to obtain the value valuation model and returning comprises:
and uploading the local training models to the central server, so that the central server performs iterative training on the local training models with the same feature class in the local training models received from the data mechanisms until convergence, and obtaining and returning value evaluation models corresponding to the feature classes.
9. A system for valuing an intangible asset, the system comprising:
the receiving module is used for receiving initial value evaluation results uploaded by all data organizations and used for carrying out value evaluation on intangible assets to be evaluated, wherein the initial value evaluation results are obtained by inputting target characteristic data of the intangible assets to be evaluated into a value evaluation model obtained based on federal learning training and predicting the target characteristic data of the intangible assets to be evaluated by all the data organizations;
the comprehensive evaluation module is used for integrating the initial value evaluation results received from the data mechanisms to obtain the comprehensive value evaluation result of the intangible asset to be evaluated;
wherein, the value evaluation system of intangible assets further comprises:
the extraction module is used for extracting target characteristic data of the intangible asset to be evaluated;
the initial evaluation module is used for inputting the target characteristic data into a value evaluation model to obtain an initial value evaluation result of the intangible asset to be evaluated, wherein the value evaluation model is obtained based on federal learning training;
and the transmission module is used for uploading the initial value evaluation result to a central server so that the central server can integrate the initial value evaluation results received from the data mechanisms to obtain a comprehensive value evaluation result of the intangible asset to be evaluated.
10. The system for valuing an intangible asset of claim 9, wherein the system for valuing an intangible asset further comprises:
and the recording module is used for recording the contribution degree of each data mechanism to the value evaluation model by combining a block chain technology.
11. A terminal device, characterized in that the terminal device comprises: a memory, a processor and a value assessment program of an intangible asset stored on the memory and executable on the processor, the value assessment program of an intangible asset when executed by the processor implementing the steps of the method of assessing the value of an intangible asset of any one of claims 1 to 3 or claims 4 to 8.
12. A storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for valuing an intangible asset of any one of claims 1 to 3 or claims 4 to 8.
CN202010370244.4A 2020-04-30 2020-04-30 Method and system for evaluating value of intangible asset, terminal equipment and storage medium Pending CN111539774A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010370244.4A CN111539774A (en) 2020-04-30 2020-04-30 Method and system for evaluating value of intangible asset, terminal equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010370244.4A CN111539774A (en) 2020-04-30 2020-04-30 Method and system for evaluating value of intangible asset, terminal equipment and storage medium

Publications (1)

Publication Number Publication Date
CN111539774A true CN111539774A (en) 2020-08-14

Family

ID=71980246

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010370244.4A Pending CN111539774A (en) 2020-04-30 2020-04-30 Method and system for evaluating value of intangible asset, terminal equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111539774A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112132198A (en) * 2020-09-16 2020-12-25 建信金融科技有限责任公司 Data processing method, device and system and server
CN112132676A (en) * 2020-09-16 2020-12-25 建信金融科技有限责任公司 Method and device for determining contribution degree of joint training target model and terminal equipment
CN112597542A (en) * 2020-12-04 2021-04-02 光大科技有限公司 Target asset data aggregation method and device, storage medium and electronic device
CN113191870A (en) * 2021-01-19 2021-07-30 迅鳐成都科技有限公司 Intellectual property value evaluation method and system based on block chain
CN113269359A (en) * 2021-05-20 2021-08-17 深圳易财信息技术有限公司 User financial status prediction method, device, medium, and computer program product
CN113553377A (en) * 2021-07-21 2021-10-26 湖南天河国云科技有限公司 Data sharing method and device based on block chain and federal learning

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112132198A (en) * 2020-09-16 2020-12-25 建信金融科技有限责任公司 Data processing method, device and system and server
CN112132676A (en) * 2020-09-16 2020-12-25 建信金融科技有限责任公司 Method and device for determining contribution degree of joint training target model and terminal equipment
CN112132198B (en) * 2020-09-16 2021-06-04 建信金融科技有限责任公司 Data processing method, device and system and server
CN112132676B (en) * 2020-09-16 2021-07-09 建信金融科技有限责任公司 Method and device for determining contribution degree of joint training target model and terminal equipment
CN112597542A (en) * 2020-12-04 2021-04-02 光大科技有限公司 Target asset data aggregation method and device, storage medium and electronic device
CN112597542B (en) * 2020-12-04 2023-10-24 光大科技有限公司 Aggregation method and device of target asset data, storage medium and electronic device
CN113191870A (en) * 2021-01-19 2021-07-30 迅鳐成都科技有限公司 Intellectual property value evaluation method and system based on block chain
CN113191870B (en) * 2021-01-19 2023-08-08 迅鳐成都科技有限公司 Intellectual property value evaluation method and system based on blockchain
CN113269359A (en) * 2021-05-20 2021-08-17 深圳易财信息技术有限公司 User financial status prediction method, device, medium, and computer program product
CN113553377A (en) * 2021-07-21 2021-10-26 湖南天河国云科技有限公司 Data sharing method and device based on block chain and federal learning
CN113553377B (en) * 2021-07-21 2022-06-21 湖南天河国云科技有限公司 Data sharing method and device based on block chain and federal learning

Similar Documents

Publication Publication Date Title
CN111539774A (en) Method and system for evaluating value of intangible asset, terminal equipment and storage medium
CN111125512B (en) Service recommendation processing method, device and system
US9300672B2 (en) Managing user access to query results
CN111340558B (en) Online information processing method, device, equipment and medium based on federal learning
US11263699B1 (en) Systems and methods for leveraging remotely captured images
CN110378749B (en) Client similarity evaluation method and device, terminal equipment and storage medium
KR101996797B1 (en) Method for providing transaction security analysis service for risk management in real estate transaction based on disclosure data and statistics
CN103294816A (en) Method and system for recommending positions for job seeker
CN111681091B (en) Financial risk prediction method and device based on time domain information and storage medium
CN111652087B (en) Car inspection method, device, electronic equipment and storage medium
CN111402471A (en) Personnel processing mode determining method and device and data processing platform
CN111159587A (en) User access information processing method and device and terminal equipment
CN111489255A (en) Data credit granting method, device, equipment and computer readable storage medium
CN112633925A (en) Method and device for evaluating value of article, computer equipment and storage medium
CN113656123A (en) Information evaluation method, device and system for equal protection evaluation
CN109450942B (en) A kind of safety detection method and its detection device of laboratory management system for internet of things
CN109087109B (en) Mobile payment confirmation method, device, system and storage medium
US20100042446A1 (en) Systems and methods for providing core property review
CN117172795A (en) Intelligent technical service fee online consultation system
CN116308497A (en) Data processing method and device
CN115880077A (en) Recommendation method and device based on client label, electronic device and storage medium
KR102562186B1 (en) System for providing rental property management based official letter sending service
CN113327161A (en) Intelligent wind control decision system for credit business
CN110362981B (en) Method and system for judging abnormal behavior based on trusted device fingerprint
CN113269614A (en) Quick merchant registration order receiving method and device, electronic equipment and readable medium

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