Business evaluation method, apparatus, device, and medium

Abstract

The application discloses an enterprise evaluation method and device, equipment and a medium. The method comprises the following steps: acquiring a scientific and technological innovation capability index of a to-be-tested enterprise, wherein the scientific and technological innovation capability index of the to-be-tested enterprise reflects the quantity and quality of innovation achievements of the to-be-tested enterprise; calculating the distribution of the scientific and technological innovation capability index of the to-be-tested enterprise; determining a customer group to which the to-be-tested enterprise belongs, and outputting an evaluation result of the to-be-tested enterprise based on an enterprise evaluation model corresponding to the customer group; wherein the enterprise evaluation model is obtained based on an automatic machine learning iteration method. The method can scientifically and effectively evaluate the scientific and technological innovation capability of an enterprise. The application can be applied to the financial field, credit evaluation or other fields.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to an enterprise evaluation method and device, equipment and medium. BACKGROUND

[0002] The scientific and technological innovation capability is one of the important factors for the growth of a scientific and technological enterprise. According to the scientific and technological innovation capability of an enterprise, the customer group of the enterprise can be evaluated differently, and a quantitative result of increasing credibility can be obtained. Financial institutions can formulate corresponding strategies according to the quantitative result of increasing credibility, so as to accurately invest credit funds in excellent scientific and technological innovation enterprises and reduce credit risks.

[0003] In the related art, the scientific and technological innovation capability of an enterprise is usually evaluated manually. This method is easily affected by manual work and can lead to a result with low credibility. SUMMARY

[0004] The main purpose of the present application is to provide an enterprise evaluation method and device, equipment and medium, which can scientifically and effectively evaluate the scientific and technological innovation capability of an enterprise and reduce the credit risk of a financial institution.

[0005] The first aspect of the present application discloses an enterprise evaluation method for an electronic device, which comprises: obtaining a scientific and technological innovation capability index of a to-be-tested enterprise, the scientific and technological innovation capability index reflecting the quantity and quality of the innovation results of the to-be-tested enterprise; calculating the distribution of the scientific and technological innovation capability index of the to-be-tested enterprise; determining the customer group to which the to-be-tested enterprise belongs, and outputting the evaluation result of the to-be-tested enterprise based on the enterprise evaluation model corresponding to the customer group; wherein the enterprise evaluation model is obtained based on an automatic machine learning iteration method, and the iteration method comprises: calculating the scientific and technological innovation capability index of a sample enterprise, the scientific and technological innovation capability index reflecting the quantity and quality of the innovation results of the sample enterprise; calculating the distribution of the scientific and technological innovation capability index of the sample enterprise; dividing the sample enterprise into a plurality of customer groups based on the distribution of the scientific and technological innovation capability index of the sample enterprise; and training the enterprise evaluation model using the sample enterprises of the plurality of customer groups until the model converges.

[0006] In a possible implementation of the above first aspect, the determination of the customer group to which the to-be-tested enterprise belongs further comprises: when the distribution of the scientific and technological innovation capability index of the to-be-tested enterprise and the scientific and technological innovation capability index of the sample enterprise satisfy a similarity threshold, merging the to-be-tested enterprise into the plurality of customer groups.

[0007] In a possible implementation of the above first aspect, when the distribution of the scientific and technological innovation capability index of the to-be-tested enterprise and the scientific and technological innovation capability index of the sample enterprise do not satisfy the similarity threshold, the to-be-tested enterprise is divided into a new customer group.

[0008] In a possible implementation of the first aspect, the method further comprises adjusting the evaluation result of the sample enterprise according to post-loan default badness and marketing effect of the enterprise.

[0009] In a possible implementation of the first aspect, the science and technology innovation capability indicator comprises at least one of invention patent application authorization, invention application publication, utility model patent application authorization, software copyright, published technical articles, and obtained science and technology awards.

[0010] In a possible implementation of the first aspect, the science and technology innovation capability indicator is adjusted based on an industry.

[0011] The second aspect of the present application discloses an enterprise evaluation device, which comprises a first calculation module for calculating a science and technology innovation capability indicator of a to-be-tested enterprise, the science and technology innovation capability indicator reflecting the quantity and quality of the innovation achievements of the to-be-tested enterprise; a second calculation module for calculating the distribution of the science and technology innovation capability indicator of the to-be-tested enterprise; an evaluation module for determining the customer group to which the to-be-tested enterprise belongs and outputting the evaluation result of the to-be-tested enterprise based on the enterprise evaluation model corresponding to the customer group; a model training module for calculating the science and technology innovation capability indicator of a sample enterprise, the science and technology innovation capability indicator reflecting the quantity and quality of the innovation achievements of the sample enterprise; calculating the distribution of the science and technology innovation capability indicator of the sample enterprise; dividing the sample enterprise into a plurality of customer groups based on the distribution of the science and technology innovation capability indicator of the sample enterprise; and training the enterprise evaluation model using the sample enterprises of the plurality of customer groups until the model converges.

[0012] In a possible implementation of the second aspect, the determination of the customer group to which the to-be-tested enterprise belongs comprises merging the to-be-tested enterprise into the plurality of customer groups when the distribution of the science and technology innovation capability indicator of the to-be-tested enterprise and the science and technology innovation capability indicator of the sample enterprise satisfy a similarity threshold.

[0013] In a possible implementation of the second aspect, the to-be-tested enterprise is divided into a new customer group when the distribution of the science and technology innovation capability indicator of the to-be-tested enterprise and the science and technology innovation capability indicator of the sample enterprise do not satisfy the similarity threshold.

[0014] In a possible implementation of the second aspect, the model training module is further configured to adjust the evaluation result of the sample enterprise according to post-loan default badness and marketing effect of the sample enterprise.

[0015] In a possible implementation of the second aspect, the science and technology innovation capability indicator comprises at least one of invention patent application authorization, invention application publication, utility model patent application authorization, software copyright, published technical articles, and obtained science and technology awards.

[0016] In a possible implementation of the second aspect, the model training module is further configured to adjust the technological innovation capability index based on an industry.

[0017] The third aspect of the present application discloses an electronic device, comprising a memory storing computer executable instructions and a processor; when the instructions are executed by the processor, the device implements the evaluation method of the first aspect of the present application.

[0018] The fourth aspect of the present application discloses a computer readable storage medium, which stores one or more computer programs, and the one or more computer programs are executed by one or more processors to make the processors execute the evaluation method of the first aspect of the present application.

[0019] The fifth aspect of the present application discloses a computer program product, comprising a computer program, which is executed by a processor to implement the evaluation method of the first aspect of the present application.

[0020] According to the enterprise evaluation method and the device, the medium and the equipment thereof, the technological innovation capability index reflecting the quantity and quality of the innovation achievements of the to-be-tested enterprise is calculated, and the distribution of the technological innovation capability index is calculated, and the enterprise evaluation model is trained by combining the distribution of the technological innovation capability index and the distribution of the technological innovation capability index of the known enterprise group. The present application provides a scientific and effective way to evaluate the innovation capability of an enterprise, which can provide credit support for accurately providing excellent technological innovation enterprises and reduce credit risks. In addition, the present application supports various technical evaluation indexes, so that the trained enterprise evaluation model can be dynamically expanded. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0022] Figure 1 The flowchart of the training method 100 of the enterprise evaluation model of an embodiment of the present application;

[0023] Figure 2 The flowchart of the enterprise evaluation method 200 of an embodiment of the present application;

[0024] Figure 3 The flowchart of the enterprise evaluation method 300 of an embodiment of the present application;

[0025] Figure 4is a flowchart of a method 400 for enterprise group division level according to an embodiment of the present application;

[0026] Figure 5 is a structural diagram of an enterprise evaluation model 500 according to an embodiment of the present application;

[0027] Figure 6 is a structural diagram of an enterprise evaluation device 600 according to an embodiment of the present application;

[0028] Figure 7 is a structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] The present application will be further described below in conjunction with specific embodiments and drawings. It can be understood that the illustrative embodiments of the present application include, but are not limited to, enterprise evaluation methods and devices, equipment, media and computer program products, and the specific embodiments described herein are merely intended to explain the present application, rather than limit the present application. In addition, for the sake of description, only the parts related to the present application are shown in the drawings, rather than all the structures or processes.

[0030] The present application will be further described below in conjunction with specific embodiments and drawings. It can be understood that the illustrative embodiments of the present application include, but are not limited to, enterprise evaluation methods and devices, equipment, media and computer program products, and the specific embodiments described herein are merely intended to explain the present application, rather than limit the present application. In addition, for the sake of description, only the parts related to the present application are shown in the drawings, rather than all the structures or processes.

[0031] In addition, various operations will be described as multiple discrete operations; however, the order of description is not intended to imply that these operations are ordered in that order. In particular, these operations can not be executed in the order presented.

[0032] For the purpose of making the purpose, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below in conjunction with the drawings.

[0033] The growth of a technology enterprise depends on multiple factors, such as R&D investment, technological innovation, human resources, financing ability, product and market, enterprise culture, and entrepreneur quality. In the process of evaluating the growth ability of an enterprise, the above-mentioned influencing factors need to be comprehensively considered to fully depict the characteristics and risk characteristics of the growth stage of the technology enterprise.

[0034] The technological innovation ability is an important influencing factor for the growth of a technology enterprise. A financial institution can design financial products and services covering the whole life cycle of an enterprise according to the intellectual property data resources of the enterprise, and provide preparation for continuous digital operation. In addition, the technological innovation ability of an enterprise can be used to make a differentiated evaluation of the enterprise customer group, and obtain a quantitative result of increased credibility. The financial institution can formulate corresponding marketing strategies according to the quantitative result of increased credibility, so as to accurately invest credit funds in excellent technology innovation enterprises and reduce credit risks.

[0035] In the related art, the technological innovation ability of an enterprise is usually evaluated by manual scoring or evaluation. This method is easily affected by manual work, and may lead to a result with low credibility.

[0036] To solve the above-mentioned problems, the present application uses machine learning to construct an enterprise evaluation model for quantifying the technological innovation ability of an enterprise. An embodiment of the present application provides a training method 100 of an enterprise evaluation model based on automatic learning iteration, as shown in Figure 1 .

[0037] S110, calculating a technological innovation ability index of a sample enterprise, the technological innovation ability index reflecting the quantity and quality of the innovation results of the enterprise to be measured.

[0038] The technological innovation ability index of an enterprise can include one or more of the patent rights, copyright, published technical articles, or obtained scientific and technological awards of the enterprise. The channels for obtaining these innovation results can be obtained from the announcement of the State Intellectual Property Office, or from technical databases, or from the information disclosure of the enterprise.

[0039] The sample enterprise can be various types of legal persons and non-legal persons, non-resident enterprises with a place in China, and foreign enterprises, which are not specifically limited here.

[0040] The patent, copyright, and other intellectual property rights can be data related to the sample enterprise, such as the application number and name of the patent whose applicant or patentee is the target object.

[0041] It should be noted that the acquisition, storage, use, processing, and the like of the data in the embodiments of the present application comply with the relevant provisions of the national laws and regulations.

[0042] In some examples, the net content of technological innovation achievements (T value) of an enterprise can be calculated according to different kinds of technological innovation achievements and respective weights.

[0043] The focus of innovation achievements of enterprises in different industries is different. For example, the innovation achievements of enterprises in industry A value patent rights, the innovation achievements of enterprises in industry B value software copyrights, or the innovation achievements in industry C value inventions in patent rights, and the innovation achievements of enterprises in industry D value utility models in patent rights. Therefore, the technological innovation capability index needs to not only reflect the quantity of innovation achievements of an enterprise, but also reflect the quality of each kind of innovation achievement according to the focus of different industries. When calculating the technological innovation capability index, a weight can be assigned according to the importance of each innovation achievement.

[0044] It can be understood that the index of net content of technological innovation achievements is used to evaluate the real and effective technological innovation achievements possessed by an enterprise at a certain point in time, that is, the greater the T value, the stronger the technological innovation capability of the enterprise.

[0045] S120, calculate the distribution of the technological innovation capability index of the sample enterprise.

[0046] As described above, the focus of innovation achievements of enterprises in different industries is different. The distribution pattern of the technological innovation capability index of each enterprise is not the same. In some embodiments, the technological innovation capability index of different enterprises can be directly compared based on a feature statistical extraction method, such as extracting maximum, minimum, mean, variance, etc. In other embodiments, a meta-feature vector of the technological innovation capability index can be constructed to measure similarity and detect the distribution of the index.

[0047] S130, divide the sample enterprises into multiple customer groups based on the distribution of the technological innovation capability index of the sample enterprises.

[0048] The distribution of the technological innovation capability index of an enterprise is obtained from a known sample enterprise group. In some embodiments, the evaluation of the known enterprise group can be determined according to human experience. In other embodiments, the distribution of the technological innovation capability index of the enterprises in the sample enterprise group can be determined according to a fixed difference average evaluation, or can not be determined according to a fixed difference evaluation.

[0049] S140, train an enterprise evaluation model using samples of different customer groups until the model converges.

[0050] The enterprise evaluation model is trained according to the technological innovation capability index of the sample enterprises obtained from S120-S130 and the existing sample enterprise customer group division.

[0051] An embodiment of the present application further provides an enterprise evaluation method 200, comprising:

[0052] S210, obtain the science and technology innovation capability index of the to-be-tested enterprise, which reflects the quantity and quality of the innovation achievements of the to-be-tested enterprise.

[0053] The innovation capability index of the to-be-tested enterprise can be calculated according to the innovation achievements of the to-be-tested enterprise as described in S110.

[0054] S220, calculate the distribution of the science and technology innovation capability index of the to-be-tested enterprise.

[0055] The method for calculating the distribution of the science and technology innovation capability index of the to-be-tested enterprise can be referred to S120, which will not be described here.

[0056] S230, determine the customer group to which the to-be-tested enterprise belongs, and output the evaluation result based on the enterprise evaluation model.

[0057] The customer group to which the to-be-tested enterprise belongs is determined based on the distribution of the science and technology innovation capability index of the to-be-tested enterprise, and the evaluation result of the to-be-tested enterprise is obtained by using the enterprise evaluation model trained according to the method 100.

[0058] Figure 2 The enterprise evaluation method 200 in the method 200 calculates the science and technology innovation capability index reflecting the quantity and quality of the innovation achievements of the sample enterprise, and calculates the distribution of the science and technology innovation capability index, and trains the enterprise evaluation model by combining the distribution of the science and technology innovation capability index and the existing customer group division of the sample enterprise. The method 200 provides a scientific and effective method for evaluating the innovation capability of an enterprise, which can provide credit support for accurately delivering excellent science and technology innovation enterprises and reduce credit risk. In addition, the method 200 supports multiple technical evaluation indexes, so that the trained enterprise evaluation model can be dynamically expanded.

[0059] In some embodiments, the method 200 can further include updating the enterprise evaluation model according to the similarity of the science and technology innovation capability index distribution of the to-be-tested enterprise and the sample enterprise, which can be referred to Figure 3 .

[0060] In Figure 3 , the method 300 includes the following steps.

[0061] In S310, obtain the science and technology innovation capability index distribution of the to-be-tested enterprise and the sample enterprise group.

[0062] In S320, calculate the similarity between the distribution of the science and technology innovation capability index of the to-be-tested enterprise and the distribution of the science and technology innovation capability index of the sample enterprise group.

[0063] The similarity is calculated by calculating the similarity between the distribution of the index of the to-be-tested enterprise and the distribution of the index of the known enterprise group. In some examples, the number of innovation achievements and the proportion of a certain type of innovation achievement of the to-be-tested enterprise are similar to the number of innovation achievements and the proportion of the certain type of innovation achievement of the known enterprise group, that is, the distribution of the technological innovation capability index of the to-be-tested enterprise is similar to the distribution of the technological innovation capability index of the known enterprise group.

[0064] In some embodiments, the similarity between the distribution of the technological innovation capability index of the to-be-tested enterprise and the distribution of the technological innovation capability index of the known enterprise group can be measured by calculating the distance between the two. The distance can be at least one of Euclidean distance, Manhattan distance, Chebyshev distance, and Minkowski distance.

[0065] In S330, it is judged whether the similarity calculated in S320 meets a threshold value.

[0066] The similarity calculated in S320 can be determined according to the set threshold value whether it meets the preset threshold condition.

[0067] When the similarity threshold condition is met, it indicates that the to-be-tested enterprise has a high similarity to a certain customer group to which the sample enterprise belongs, and then the to-be-tested enterprise can be divided into the corresponding customer group in S340, that is, the to-be-tested enterprise and the known customer group are merged.

[0068] When the similarity threshold condition is not met, it indicates that the to-be-tested enterprise does not belong to any existing customer group, and then a new customer group can be established in S350.

[0069] For the newly established customer group, the technological innovation capability level is calculated according to the technological innovation capability index of the to-be-tested enterprise in S360.

[0070] Figure 3 The method 300 in the embodiment calculates the similarity between the distribution of the technological innovation capability index of the to-be-tested enterprise and the distribution of the technological innovation capability index of the known enterprise group, and judges whether the to-be-tested enterprise belongs to a certain customer group of the known enterprise group according to the similarity threshold value. When the similarity threshold value is met, the to-be-tested enterprise can be merged into the known customer group, and when the similarity threshold value is not met, the to-be-tested enterprise is merged to form a new enterprise group by re-dividing the levels of the known enterprise group. Figure 3 The method adopts a statistical scientific method to automatically access an evaluation architecture, calculates the similarity of the model group, and automatically merges similar customer groups or establishes new customer groups.

[0071] Figure 4 The method 400 for dividing the levels of the enterprise group in an embodiment of the present application is shown. The method 400 includes the following steps.

[0072] In S410, a sub-customer group is divided.

[0073] According to the distribution of the technological innovation capability indexes of the to-be-tested enterprise and the distribution of the technological innovation capability indexes of the known enterprise group, each sub-group based on T grades that have been divided in the known enterprise group is re-divided. In some embodiments, the focus of the innovation achievements of different industries can be considered when dividing the sub-groups.

[0074] As mentioned above, the focus of the innovation achievements of enterprises in different industries is different. In some possible implementations of the embodiments of the present application, the industry or technical field to which an enterprise belongs can include but is not limited to: optoelectronic integration, electronics and information technology, new materials, biological medicine, new energy, environmental protection, manufacturing, laser technology, automation technology, and the like.

[0075] In S420, a quantile point is determined.

[0076] The quantile point refers to a numerical point that divides the probability distribution range of a random variable into several equal parts. Commonly used are the median (i.e., the second quantile), the quartile, the percentile, and the like. In some examples, the quantile point can be determined according to the jump point of each sub-enterprise group.

[0077] In S430, an adjustment coefficient is determined.

[0078] After the quantile point is determined, the coefficient of the technological innovation capability index of each enterprise in the enterprise group can be adjusted. In some examples, the adjustment coefficient can be externally input. In some examples, the coefficient of the technological innovation capability index of each enterprise can be adjusted based on the industry characteristics.

[0079] In S440, a T grade is calculated.

[0080] Based on the division of each sub-group based on T grades and the determined quantile point, the coefficients of the related business indexes are adjusted, and finally the T grade result is determined.

[0081] In some embodiments, the rationality of the T grade division result can be verified to test the effectiveness of the increased confidence result. In the result of the T grade division, the effectiveness of the increased confidence can be tested by testing the post-loan default rate of the head customers, the marketing benefits, and the like. For the to-be-tested enterprises that meet the test indexes, it indicates that the trained enterprise evaluation model operates well. For the to-be-tested enterprises that do not meet the test indexes, it indicates that the trained enterprise evaluation model still needs to be adjusted. In some embodiments, the overall model risk is evaluated according to the result of the model verification, corresponding model risk warnings are performed, and a report of the model verification can be automatically generated.

[0082] Reference is now made to Figure 5 , Figure 5The expansion of the enterprise evaluation model 500 of one embodiment of the present application is shown. In the enterprise evaluation model 500, when a new technological innovation capability index 510 needs to be added, the corresponding threshold value 520 can be calculated according to the newly added index, and the index of each enterprise is reclassified 550. The new technological innovation capability index can be an index other than the technological innovation capability index in the original enterprise evaluation model 500, for example, an enterprise's technology entering the national or regional high-tech technology list. When the evaluation of each enterprise in the newly added customer group 530 is needed, the consistency 540 between the newly added customer group and the original customer group in the enterprise evaluation model 500 can be verified, and the T level 550 is determined by the consistency result. When the consistency is met, the new customer group and the original customer group are merged, and if the consistency is not met, the T level of the customer group is reclassified.

[0083] Figure 5 The expansion of the enterprise evaluation model shows that the enterprise evaluation model of the present application can meet the technical richness and business development needs. Through the automatic machine learning model iteration method, the corresponding extension index system is modularly accessed, and different indexes can be expanded. At the same time, by calculating the similarity of the model group performance, the similar customer groups are automatically merged or the new customer group T level evaluation index system is established, which provides a unified architecture that can expand different customer groups.

[0084] Reference Figure 6 , Figure 6 The structure diagram of the enterprise evaluation device 600 in one embodiment of the present application is shown. The device 600 includes:

[0085] The first calculation module 610 is configured to calculate the technological innovation capability index of the enterprise to be measured, and the technological innovation capability index reflects the quantity and quality of the innovation results of the enterprise to be measured.

[0086] The second calculation module 620 is configured to calculate the distribution of the technological innovation capability index of the enterprise to be measured.

[0087] The evaluation module 630 is configured to determine the customer group to which the enterprise to be measured belongs, and output the evaluation result based on the corresponding enterprise evaluation model of the customer group.

[0088] The model training module 640 is configured to calculate the technological innovation capability index of the sample enterprise, and the technological innovation capability index of the sample enterprise reflects the quantity and quality of the innovation results of the sample enterprise; calculate the distribution of the technological innovation capability index of the sample enterprise; divide the sample enterprise into multiple customer groups based on the distribution of the technological innovation capability index of the sample enterprise; and train the enterprise evaluation model using the samples of different customer groups until the model converges.

[0089] Figure 6The enterprise evaluation device 600 in the embodiment calculates a scientific and technological innovation capability index reflecting the quantity and quality of the innovation achievements of the enterprise to be measured, and calculates the distribution of the scientific and technological innovation capability index. The enterprise evaluation model is trained by combining the distribution of the scientific and technological innovation capability index and the distribution of the scientific and technological innovation capability index of the known enterprise group. The device 600 provides a scientific and effective way to evaluate the innovation capability of the enterprise, which can provide credit support for accurate delivery of excellent scientific and technological innovation enterprises and reduce credit risk. In addition, the device 600 supports multiple technical evaluation indexes, so that the trained enterprise evaluation model can be dynamically expanded.

[0090] In addition, Figure 6 The enterprise evaluation device 600 in the embodiment can use the method in each of the above embodiments when evaluating the enterprise, which will not be repeated here.

[0091] Now referring to Figure 7 , a block diagram of an electronic device 700 according to one embodiment of the present application is shown. The device 700 can include one or more processors 702, system control logic 708 connected to at least one of the processors 702, system memory 704 connected to the system control logic 708, non-volatile memory (NVM) 706 connected to the system control logic 708, and a network interface 710 connected to the system control logic 708.

[0092] The processor 702 can include one or more single core or multi core processors. The processor 702 can include any combination of general-purpose processors and dedicated processors (e.g., graphics processors, application processors, baseband processors, etc.). In embodiments herein, the processor 702 can be configured to perform one or more embodiments in accordance with various embodiments as shown in Figures 1-6 .

[0093] In some embodiments, the system control logic 708 can include any suitable interface controllers to provide for any suitable interface to at least one of the processors 702 and / or any suitable device or component in communication with the system control logic 708.

[0094] In some embodiments, the system control logic 708 can include one or more memory controllers to provide an interface to connect to the system memory 704. The system memory 704 can be used to load and store data and / or instructions. In some embodiments, the memory 704 of the device 700 can include any suitable volatile memory, such as suitable dynamic random access memory (DRAM).

[0095] The NVM / storage 706 can include one or more tangible, non-transitory computer-readable media for storage of data and / or instructions. In some embodiments, the NVM / storage 706 can include any suitable non-volatile memory and / or any suitable non-volatile storage device such as at least one of a flash memory, an HDD (Hard Disk Drive), a CD (Compact Disc) drive, and a DVD (Digital Versatile Disc) drive.

[0096] The NVM / storage 706 can include a portion of the storage resources installed on the device of the apparatus 700, or it can be accessed by the device but not necessarily a part of the device. For example, the NVM / storage 706 can be accessed over a network via the network interface 710.

[0097] In particular, the system memory 704 and the NVM / storage 706 can include, respectively, a temporary copy and a permanent copy of the instructions 720. The instructions 720 can include instructions that, when executed by at least one of the processors 702, cause the apparatus 700 to perform one or more embodiments of the methods shown in FIGS. 1-4. Figures 1-5 In some embodiments, the instructions 720, hardware, firmware, and / or software components thereof can additionally / alternatively be placed in the system control logic 708, the network interface 710, and / or the processors 702.

[0098] The network interface 710 can include a transceiver to provide a radio interface for the apparatus 700 to communicate with any other suitable devices (e.g., front-end modules, antennas, etc.) over one or more networks. In some embodiments, the network interface 710 can be integrated with other components of the apparatus 700. For example, the network interface 710 can be integrated with at least one of the processors 702, the system memory 704, the NVM / storage 706, and firmware having instructions that, when executed by at least one of the processors 702, cause the apparatus 700 to implement one or more embodiments of the various embodiments shown in FIGS. 1-4. Figures 3-6

[0099] The network interface 710 can further include any suitable hardware and / or firmware to provide a multiple-input multiple-output radio interface. For example, the network interface 710 can be a network adapter, a wireless network adapter, a telephone modem, and / or a wireless modem.

[0100] ​In one embodiment, at least one of the processors 702 can be packaged together with logic for one or more controllers of the system control logic 708 in a system in a package (SiP). In one embodiment, at least one of the processors 702 can be integrated on the same die with logic for one or more controllers of the system control logic 708 to form a system on a chip (SoC).

[0101] The device 700 can further include input / output (I / O) devices 712. The I / O devices 712 can include user interfaces that enable a user to interact with the device 700; the peripheral component interface is designed to enable peripheral components to interact with the device 700 as well. In some embodiments, the device 700 also includes sensors for determining at least one of environmental conditions and location information related to the device 700.

[0102] In some embodiments, the user interfaces can include, without limitation, displays (e.g., liquid crystal displays, touch screen displays, etc.), speakers, microphones, one or more cameras (e.g., still cameras and / or video cameras), flashlights (e.g., light-emitting diode flashlights), and keyboards.

[0103] In some embodiments, the peripheral component interface can include, without limitation, a non-volatile memory port, an audio jack, and a power interface.

[0104] In some embodiments, the sensors can include, without limitation, a gyroscope sensor, an accelerometer, a proximity sensor, an ambient light sensor, and a positioning unit. The positioning unit can also be part of, or interact with, the network interface 710 to communicate with components of a positioning network (e.g., Global Positioning System (GPS) satellites).

[0105] It is to be understood that the structure illustrated by the embodiments of the present application does not constitute a specific limitation to the device 700. In other embodiments of the present application, the device 700 can include more or fewer components than shown, or combine certain components, or split certain components, or different arrangements of components. The illustrated components can be implemented in hardware, software, or a combination of software and hardware.

[0106] The program code can be applied to input instructions to perform the functions described herein and generate output information. The output information can be applied to one or more output devices, which can be known in the art. For the purposes of this application, a processing system includes any system that has a processor, such as a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC), or a microprocessor.

[0107] The program code can be implemented in a high level of programming language or a object-oriented programming language to communicate with processing system. When necessary, the program code can also be implemented in an assembly language or a machine language. In fact, the mechanisms described herein are not limited to any specific programming language. The language can be a compiled or interpreted language, in either case, the language can be a compiled or interpreted language.

[0108] One or more aspects of at least one embodiment can be implemented by representative instructions stored on a computer-readable storage medium that represents various logic within the processor, which when read by a machine causes the machine to fabricate logic to perform the techniques described herein. Such representations, known as "IP cores" can be stored on a tangible, computer readable storage medium and supplied to various customers or manufacturing facilities to load into the fabrication machines that make the logic or processor.

[0109] One embodiment of the present application discloses a computer readable medium storing one or more programs, which can be executed by one or more processors to implement the method of Figures 1-5 .

[0110] One embodiment of the present application discloses a computer program product including a computer program, which when executed by a processor implements the method of Figures 1-5 .

[0111] Unless otherwise defined, the terms "comprising", "having", and "including" are synonymous. The phrase "A / B" means "A or B". The phrase "A and / or B" means "(A and B) or (A or B)".

[0112] As used herein, the terms "module" or "unit" can refer to, be or include an application specific integrated circuit (ASIC), an electronic circuit, a processor and / or memory (shared, dedicated, or group) that execute one or more software or firmware programs, a combinational logic circuit, and / or other suitable components that provide the described functionality.

[0113] In some cases, the disclosed embodiments can be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments can also be implemented as instructions carried by or stored on a transitory or non-transitory machine-readable (e.g., computer-readable) medium, which can be read and executed by one or more processors. For example, the instructions can be distributed over the network or by way of other computer readable media to cause a variety of computing systems or machines to perform the tasks outlined herein. Thus, the machine- readable medium can include any mechanism that stores or transmits information in a form readable by a machine (e.g., a computer), but is not limited to, soft disks, optical disks, magnetic disks or tapes, ROM (read only memory), RAM (random access memory), EPROM (erasable programmable ROM), EEPROM (electrically erasable programmable ROM), floppy disks, optical disks, magnetic disks, memory cards, and the like. Thus, a machine-readable medium includes any type of medium for storing or transmitting electronic instructions or information in a form readable by a machine (e.g., a computer).

[0114] In the drawings, some of the structural or methodological acts can be shown in a particular arrangement and / or order. However, it should be understood that such is merely an example, and that the acts can be arranged and / or ordered differently without departing from the scope of the embodiments. Moreover, not all illustrated acts can be required to implement a methodology in accordance with the embodiments, and those acts can be implemented in an order other than that shown.

[0115] It should be understood that although terms such as "first" and "second" can be used herein to describe various elements or data, these elements or data should not be limited by these terms. These terms are only used to distinguish one feature from another. For example, a first feature could be termed a second feature, and, similarly, a second feature could be termed a first feature without departing from the scope of the example embodiments.

[0116] It should be noted that in the description of the specification, like numbers in two or more figures represent the same or similar elements unless otherwise indicated. While the specification concludes with claims particularly pointing out and distinctly claiming that which is regarded as the application, it is anticipated that the application can include more than what is literally claimed as it pertains to the scope of the claims.

Claims

1. A method for evaluating enterprises, used for electronic devices, characterized in that, The enterprise evaluation methods include: Obtain the technological innovation capability index of the enterprise under test, which reflects the quantity and quality of the enterprise's innovative achievements; Calculate the distribution of the technological innovation capability index of the enterprise under test, whereby the distribution of the technological innovation capability index represents the proportion of each type of innovation achievement of the enterprise under test in the total number of innovation achievements; The customer group to which the enterprise to be tested belongs is determined, and the evaluation result of the enterprise to be tested is output based on the enterprise evaluation model corresponding to the customer group. Determining the customer group to which the enterprise to be tested belongs includes: When the distribution of the technological innovation capability index of the enterprise under test and the technological innovation capability index of the sample enterprises meet the similarity threshold, the enterprise under test will be merged into the customer group. When the distribution of the technological innovation capability index of the enterprise under test and the technological innovation capability index of the sample enterprises do not meet the similarity threshold, the customer groups to which the enterprise under test belongs are reclassified based on the determined quantiles and relevant business indicator coefficients. The enterprise evaluation model is obtained based on an automated machine learning iterative method, which includes: Calculate the technological innovation capability index of the sample enterprises, which reflects the quantity and quality of their innovative achievements. Calculate the distribution of the technological innovation capability index of the sample enterprises; Based on the distribution of the technological innovation capability indicators of the sample enterprises, the sample enterprises are divided into multiple customer groups. The enterprise evaluation model is trained using the sample enterprises from the multiple customer groups until the model converges; and When a new technological innovation capability indicator is added, the corresponding similarity threshold is calculated; or when a new customer group is introduced, the enterprise evaluation model is automatically iterated.

2. The method according to claim 1, characterized in that, The iterative method also includes adjusting the evaluation results of the sample enterprises based on their post-loan defaults and marketing effects.

3. The method according to claim 2, characterized in that, The technological innovation capability indicators include at least one of the following: invention patent application authorization, invention application publication, utility model patent application authorization, software copyright, published technical articles, and obtained science and technology awards.

4. The method according to claim 1, characterized in that, The iterative method also includes adjusting the technological innovation capability indicators based on industry trends.

5. A company evaluation device, characterized in that, The device includes, The first calculation module is used to calculate the technological innovation capability index of the enterprise under test, which reflects the quantity and quality of the enterprise's innovative achievements. The second calculation module is used to calculate the distribution of the technological innovation capability index of the enterprise under test, wherein the distribution of the technological innovation capability index represents the proportion of each type of innovation achievement of the enterprise under test in the total number of innovation achievements; The evaluation module is used to determine the customer group to which the enterprise under test belongs, and output the evaluation result of the enterprise under test based on the enterprise evaluation model corresponding to the customer group. Determining the customer group to which the enterprise under test belongs includes: When the distribution of the technological innovation capability index of the enterprise under test and the technological innovation capability index of the sample enterprises meet the similarity threshold, the enterprise under test will be merged into the customer group. When the distribution of the technological innovation capability index of the enterprise under test and the technological innovation capability index of the sample enterprises do not meet the similarity threshold, the customer groups to which the enterprise under test belongs are reclassified based on the determined quantiles and relevant business indicator coefficients. The model training module is used to calculate the technological innovation capability index of the sample enterprises, which reflects the quantity and quality of their innovative achievements; calculate the distribution of the technological innovation capability index of the sample enterprises; divide the sample enterprises into multiple customer groups based on the distribution of the technological innovation capability index; train the enterprise evaluation model using the sample enterprises in the multiple customer groups until the model converges; and calculate the corresponding similarity threshold when a new technological innovation capability index is added; or automatically iterate the enterprise evaluation model when a new customer group is introduced.

6. The apparatus according to claim 5, characterized in that, The model training module is also used to adjust the evaluation results of the sample enterprises based on their post-loan defaults and marketing effects.

7. The apparatus according to claim 6, characterized in that, The technological innovation capability indicators include at least one of the following: invention patent application authorization, invention application publication, utility model patent application authorization, software copyright, published technical articles, and obtained science and technology awards.

8. The apparatus according to claim 5, characterized in that, The model training module is also used to adjust the technological innovation capability index based on industry.

9. An electronic device, characterized in that, The device includes a memory storing computer-executable instructions and a processor; when the instructions are executed by the processor, the device performs the evaluation method according to any one of claims 1 to 4.

10. A computer-readable medium, characterized in that, The medium stores one or more programs, which can be executed by one or more processors to implement the evaluation method according to any one of claims 1 to 4.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the evaluation method as described in any one of claims 1 to 4.

Images