Inter-enterprise contact active construction method and system based on artificial intelligence

Abstract

The invention relates to the technical field of data processing, and provides an inter-enterprise contact active construction method and system based on artificial intelligence. The method comprises the following steps: at least based on a demand of a first enterprise initiating contact, obtaining a candidate second enterprise pool meeting the demand through artificial intelligence, grading the first demand according to an importance degree, and determining the number of to-be-contacted enterprises and an active contact strategy according to different types of sub-demands, so as to meet the personalized demand of a demand side enterprise; and the enterprise contact efficiency is improved on the basis of reducing the enterprise contact cost.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method and system for actively constructing enterprise - to - enterprise connections based on artificial intelligence. Background Art

[0002] During the production and operation process, enterprises (demanders) face various demands for products or technical services provided by other enterprises (providers). How to quickly and efficiently contact enterprises with supply - demand matching has always been a difficult problem in the industry.

[0003] To solve this problem, the existing solution is to build a unified access platform for demand - side enterprises and supply - side enterprises. Demand - side enterprises can publish demands through the platform and passively wait for supply - side enterprises to respond to the demands, or the platform recommends supply - side enterprises to demand - side enterprises based on demand matching degree. However, this method is relatively passive for demand - side enterprises and it is difficult to meet the personalized needs of demand - side enterprises.

[0004] Therefore, how to provide a method for actively constructing enterprise - to - enterprise connections to meet the personalized needs of demand - side enterprises is an urgent problem to be solved in this field. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for actively constructing enterprise - to - enterprise connections based on artificial intelligence, so as to at least partially solve the above problems.

[0006] According to one aspect of the present disclosure, a method for actively constructing enterprise - to - enterprise connections based on artificial intelligence is proposed, including: obtaining a candidate pool of second enterprises that meet the first demand based at least on the first demand of the first enterprise initiating the connection; determining the number and priority of the second enterprises to be contacted in the candidate pool of second enterprises; wherein, the first demand includes a first - type sub - demand and a second - type sub - demand, determining a first number of second enterprises of the first type based on the first - type sub - demand, and determining a second number of second enterprises of the second type based on the second - type sub - demand; wherein, the importance degree of the first - type sub - demand is higher than that of the second - type sub - demand, and the first number is less than the second number; based on determining the number and priority of the second enterprises to be contacted, actively establish a connection between the first enterprise and the second enterprises and determine the intended cooperation enterprises based on the connection situation.

[0007] Optionally, the obtaining a candidate pool of second enterprises that meet the first demand based at least on the first demand of the first enterprise initiating the connection includes inputting the first demand into a pre - trained deep - learning model, and obtaining the candidate pool of second enterprises that meet the first demand based on the output of the pre - trained deep - learning model.

[0008] Optionally, actively establishing a connection between the first enterprise and the second enterprise and determining the intended cooperative enterprise based on the connection situation includes that the first enterprise actively establishes a connection with one or more of the first type of second enterprises with the first quantity at the same time, and takes all the first type of second enterprises with the first quantity as the intended cooperative enterprises.

[0009] Optionally, actively establishing a connection between the first enterprise and the second enterprise and determining the intended cooperative enterprise based on the connection situation includes dividing the second type of second enterprises with the second quantity into two categories, namely the third type of enterprises and the fourth type of enterprises. Among them, the third type of enterprises are the enterprises that have a cooperation history with the first enterprise, and the fourth type of enterprises are the enterprises that have a cooperation history with the third enterprise similar to the first enterprise. For the third type of enterprises, the first enterprise actively establishes a connection with the third preset quantity of the third type of enterprises at one time or multiple times, and takes the fourth preset quantity of enterprises as the intended cooperative enterprises. For the fourth type of enterprises, the first enterprise actively establishes a connection with the fifth preset quantity of the fourth type of enterprises at one time or multiple times, and takes the sixth preset quantity of enterprises as the intended cooperative enterprises. Among them, the third preset quantity is less than the fifth preset quantity, and the fourth preset quantity is greater than the sixth preset quantity.

[0010] According to one aspect of the present disclosure, an active construction system for inter-enterprise connection based on artificial intelligence is proposed, including: a first acquisition module, configured to acquire a candidate second enterprise pool that meets the first demand at least based on the first demand of the first enterprise initiating the connection; a first determination module, configured to determine the quantity and priority of the second enterprises to be contacted in the candidate second enterprise pool; wherein, the first demand includes a first type of sub-demand and a second type of sub-demand, determining a first quantity of the first type of second enterprises based on the first type of sub-demand, and determining a second quantity of the second type of second enterprises based on the second type of sub-demand; wherein, the importance degree of the first type of sub-demand is higher than that of the second type of sub-demand, and the first quantity is less than the second quantity; a connection establishment module, configured to actively establish a connection between the first enterprise and the second enterprise based on the determined quantity and priority of the second enterprises to be contacted and determine the intended cooperative enterprise based on the connection situation.

[0011] Optionally, the first acquisition module is further configured to input the first demand into a pre-trained deep learning model, and acquire a candidate second enterprise pool that meets the first demand based on the output of the pre-trained deep learning model.

[0012] Optionally, the connection establishment module is configured to actively establish a connection with one or more of the first type of second enterprises with the first quantity by the first enterprise, and take all the first type of second enterprises with the first quantity as the intended cooperative enterprises.

[0013] Optionally, the contact establishment module classifies the second-type second enterprises of the second quantity into two categories, namely the third-type enterprises and the fourth-type enterprises. Among them, the third-type enterprises are the enterprises that have a cooperation history with the first enterprise, and the fourth-type enterprises are the enterprises that have a cooperation history with the third enterprise similar to the first enterprise. For the third-type enterprises, the first enterprise actively establishes contacts with a third preset quantity of third-type enterprises at one time or multiple times, and takes a fourth preset quantity of the enterprises as potential cooperation enterprises. For the fourth-type enterprises, the first enterprise actively establishes contacts with a fifth preset quantity of fourth-type enterprises at one time or multiple times, and takes a sixth preset quantity of the enterprises as potential cooperation enterprises. Among them, the third preset quantity is less than the fifth preset quantity, and the fourth preset quantity is greater than the sixth preset quantity.

[0014] The present disclosure also provides a computer-readable storage medium storing a computer program, characterized in that: when the computer program is run by a processor, it executes the steps in the method described in any one of the above embodiments.

[0015] An embodiment of the present application also provides an electronic device, where the electronic device includes a memory and a processor. A computer program is stored in the memory, and the processor executes the steps in the method described in any one of the above embodiments by calling the computer program stored in the memory.

[0016] The present invention relates to a method for actively constructing inter-enterprise contacts based on artificial intelligence. The method includes, at least based on the needs of the first enterprise initiating the contact, obtaining a candidate pool of second enterprises that meet the needs through artificial intelligence, grading the first needs according to the importance level, and determining the number of enterprises to be contacted and the active contact strategy according to different types of sub-needs, so as to meet the personalized needs of the demanding enterprise and improve the efficiency of enterprise contacts on the basis of reducing the enterprise contact cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of a method for actively constructing inter-enterprise contacts based on artificial intelligence provided by an embodiment of the present application.

[0018] Figure 2 It is a schematic diagram of a system for actively constructing inter-enterprise contacts based on artificial intelligence provided by an embodiment of the present application.

[0019] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application.

[0020] Figure 4 It is a schematic diagram of the platform architecture provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The following further describes the specific embodiments of the present invention in conjunction with the accompanying drawings. It should be noted here that the description of these embodiments is used to help understand the present invention, but does not limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0022] It should be noted that in this application, "first", "second" and various numerical numbers are used for distinction for the convenience of description, and do not limit the scope of the embodiments of this application. For example, to distinguish different classification results, etc., rather than for describing a specific order or sequence. It should be understood that the objects described in this way can be interchanged under appropriate circumstances so as to be able to describe the solutions other than the embodiments of this application.

[0023] Specifically, Figure 1 The following shows a specific implementation flowchart of a method for actively constructing enterprise - to - enterprise connections based on artificial intelligence provided by an embodiment of this application. Please refer to Figure 1 For the method for actively constructing enterprise - to - enterprise connections based on artificial intelligence provided by this application, the specific steps are as follows: Step S1, based on the first demand of the first enterprise initiating the connection, obtain a candidate second - enterprise pool that meets the first demand.

[0024] In this embodiment, as Figure 4 shown, multiple enterprises are pre - registered on the same cloud platform. Each registered enterprise sets a corresponding Agent based on the question - answering large - model, and each Agent runs on its own terminal. Among them, the question - answering large - model can be constructed and trained based on Transformer, and the specific construction and training process will not be elaborated here.

[0025] Specifically, taking enterprise A as an example, enterprise A plans to find a supplier to meet its production needs. First, enterprise A publishes its first demand on the platform and actively initiates a connection through Agent - A or the cloud platform, waiting for a matching enterprise to respond. The first demand includes, but is not limited to, information such as the specification requirements for raw materials (or product components) and supply capacity. After receiving this demand, the platform retrieves the enterprise database and filters out a candidate second - enterprise pool that meets the demand.

[0026] In some embodiments, to improve the matching accuracy, the second enterprises are screened by means of artificial intelligence. For example, the corresponding second enterprises can be matched through a deep learning model. Specifically, the first demand of enterprise A is input into a pre-trained deep learning model. It can be understood that this deep learning model is trained based on a large amount of enterprise information data (including the business fields, technical expertise, production capacity, past cooperation cases, etc. of enterprises). Through the analysis of the input demand, the model outputs a candidate pool of second enterprises that meet the demand. For example, through model operation, 100 enterprises are selected as the candidate pool of second enterprises. These enterprises have a certain degree of matching with the demand of enterprise A in terms of technology R & D ability, production and manufacturing ability, etc. Further, the selected enterprises can be sorted based on the matching degree. It can be understood that the corresponding number of second enterprise pools can be screened according to actual needs, and this embodiment does not make any restrictions.

[0027] Specifically, the deep learning model adopted in this embodiment is based on a multi-layer neural network architecture. For example, it can be a deep neural network (DNN) or more complex convolutional neural network (CNN), recurrent neural network (RNN) and its variants (such as long short-term memory network LSTM), etc., and this embodiment does not make any restrictions. Taking DNN as an example, it consists of an input layer, multiple hidden layers and an output layer. The input layer is responsible for receiving the demand data of the first enterprise. The hidden layer extracts features and performs complex transformations on the input data through a large number of neurons. The output layer then outputs a candidate pool of second enterprises that meet the demand.

[0028] The model training process includes: 1) Data preprocessing: Clean the collected raw data to remove duplicate, incorrect or incomplete data. Standardize and normalize various types of data to make them have a unified dimension and value range, which is convenient for the model to learn. For text data (such as enterprise business descriptions, technical expertise, cooperation cases, etc.), natural language processing techniques are used for lexical and syntactic analysis to convert it into a vector form that can be understood by a computer, such as word vectors or sentence vectors.

[0029] 2) Model initialization: Initialize the parameters of the DNN model, including the connection weights and bias terms between neurons in each layer. A random initialization method is adopted, but in order to accelerate the convergence speed and improve the training stability, some specific initialization methods can also be used, such as Xavier initialization or Kaiming initialization, and this embodiment does not make any restrictions.

[0030] 3) Model training: During the training process, the enterprise demand data (input data) in the training set is input into the model. The model calculates the prediction result (i.e., the candidate second enterprise pool) through forward propagation. The prediction result is compared with the real enterprise data that meets the demand (label data), and a suitable loss function (such as cross-entropy loss function or mean squared error loss function, etc.) is used to calculate the difference between the prediction result and the real result. Then, through the backpropagation algorithm, the parameters of the model are updated according to the gradient information of the loss function, so that the value of the loss function continuously decreases, that is, the prediction result of the model continuously approaches the real result. During the training process, optimization algorithms such as Batch Gradient Descent, Stochastic Gradient Descent, or Mini - Batch Gradient Descent are usually used to accelerate the convergence of the model, and this embodiment does not make any restrictions.

[0031] 4) Model tuning: During the training process, the model is regularly evaluated using the validation set, and performance metrics such as accuracy, recall rate, and F1 value of the model on the validation set are calculated. The hyperparameters of the model are adjusted according to the evaluation results, such as increasing or decreasing the number of neurons in the hidden layer, adjusting the learning rate, changing the regularization parameter, etc., to improve the generalization ability and performance of the model. When the performance of the model on the validation set no longer improves or reaches the preset performance metrics, the training is stopped.

[0032] It should be noted that the above training process of the model is only an exemplary overview, and the detailed model training and model application processes can be specifically set according to the specific data involved in the actual application scenario.

[0033] Step S2, determine the number and priority of the second enterprises to be contacted in the candidate second enterprise pool. Among them, the first demand includes a first type of sub-demand and a second type of sub-demand. Based on the first type of sub-demand, a first number of second enterprises of the first type are determined, and based on the second type of sub-demand, a second number of second enterprises of the second type are determined. Among them, the importance degree of the first type of sub-demand is higher than that of the second type of sub-demand, and the first number is less than the second number.

[0034] In the selected candidate second enterprise pool, further analyze and determine the quantity and priority of the second enterprises to be contacted. Specifically, split the first requirement of enterprise A into a first type of sub-requirement and a second type of sub-requirement, where the importance of the first type of sub-requirement is greater than that of the second type of sub-requirement. Exemplarily, the first type of sub-requirement may be the core raw materials in the production formula, and the second type of sub-requirement may be non-core raw materials such as auxiliary materials that match the core raw materials. Or, the first type of sub-requirement may be the core components (such as bearings) of a certain component of the product, while the second type of sub-requirement may be non-core components such as brackets that match the bearings.

[0035] Based on the first type of sub-requirement, screen the enterprises that meet the conditions. Since the importance of the first type of sub-requirement is relatively high, the requirements for the supplier enterprises are also relatively high. For example, the requirements for the R & D capabilities and production and manufacturing capabilities of the supplier enterprises are very high. In this embodiment, for the second enterprises of the first type, the key considerations for the enterprises to be contacted are the production and R & D capabilities, product indicators, cooperation stability, industry reputation, etc. Price is not the main consideration factor. Therefore, for this type of sub-requirement, a relatively small number (exemplarily, such as 5, such as Figure 4 , enterprise B - enterprise F) of excellent cooperative enterprises can be selected to establish contact and communication, so as to improve the efficiency of contact and form good cooperation stickiness through long-term cooperation to ensure the quality of the final product.

[0036] For the second type of sub-requirement, because its importance to the final product is relatively low, the main principle for determining the cooperative enterprise is cost performance. In actual business negotiations, usually more enterprises are needed to find enterprises with cost advantages. Based on this, for the second type of sub-requirement, a relatively large number (exemplarily, such as 50, such as Figure 4 , enterprise G1 - enterprise G50) of cooperative enterprises can be selected to establish contact and communication to obtain production and manufacturing enterprises with cost advantages, so as to balance the production cost of the entire product. It can be understood that the first quantity and the second quantity can be specifically set according to the actual application scenario, and this embodiment does not make any limitations.

[0037] Step S3, based on the determined quantity and priority of the second enterprises to be contacted, actively establish the connection between the first enterprise and the second enterprises and determine the intended cooperative enterprises based on the connection situation.

[0038] In this embodiment, the platform first establishes the connection between the first enterprise and the second enterprises of the first type. Specifically, Agent-A of the first enterprise actively establishes the connection with the second enterprises of the first type through the platform. It can be understood that, such as Figure 4As shown, in order to improve efficiency, Agent-A can establish connections with multiple second enterprises of the first type through the platform simultaneously. For example, Agent-A can simultaneously contact the determined Agent-B, Agent-C, Agent-D, Agent-E, and Agent-F. It can be understood that due to the relatively high importance of the requirements, the number of second enterprises of the first type that can meet the requirements in all aspects is not large. Therefore, all the determined second enterprises of the first type are marked as intended cooperation enterprises, and the enterprise selects the final cooperation enterprise based on the contact situation.

[0039] After determining the intended cooperation enterprises of the second enterprises of the first type, determine the intended cooperation enterprises of the second enterprises of the second type. Specifically, the initiative to establish connections between the first enterprise and the second enterprise and determine the intended cooperation enterprises based on the contact situation includes that the second quantity of second enterprises of the second type is divided into two categories, namely the third type of enterprise and the fourth type of enterprise. Among them, the third type of enterprise is an enterprise that has had a cooperation history with the first enterprise, and the fourth type of enterprise is an enterprise that has had a cooperation history with a third enterprise similar to the first enterprise. For the third type of enterprise, the first enterprise actively establishes connections with a third preset quantity of third type of enterprises simultaneously once or multiple times, and takes a fourth preset quantity of enterprises as the intended cooperation enterprises. For the fourth type of enterprise, the first enterprise actively establishes connections with a fifth preset quantity of fourth type of enterprises simultaneously once or multiple times, and takes a sixth preset quantity of enterprises as the intended cooperation enterprises. Among them, the third preset quantity is less than the fifth preset quantity, and the fourth preset quantity is greater than the sixth preset quantity.

[0040] In this embodiment, the second enterprises of the second type include two categories. One category is the third type of enterprises that have already had a cooperation with enterprise A, and the other category is the fourth type of enterprises that have had a cooperation experience with an enterprise H similar to enterprise A. In this way, the second enterprises of the second type are all enterprises with certain industry experience and industry recognition. When enterprise A contacts them, the communication is relatively smooth, which can improve the contact efficiency. In addition, while ensuring the acquisition of cost-effective cooperation enterprises, it can also ensure a certain quality of products or services, and at the same time further enrich the supply chain of enterprise A.

[0041] Among them, the third enterprise H similar to enterprise A can be relatively similar to enterprise A in terms of industry, business model, main products, enterprise scale, etc. The quantity of H can be set according to the actual situation. At the same time, when determining the fourth type of enterprises, enterprises that have had a cooperation with multiple H enterprises can be given priority, and the more H enterprises an enterprise has cooperated with, the higher its ranking.

[0042] Furthermore, the second quantity of the second type of second enterprises may be relatively large. For example, in the previous example, the second quantity is 50 enterprises. If each of the 50 enterprises is contacted, the efficiency will undoubtedly be very low, which is not conducive to the enterprise's timely decision-making. To improve the efficiency of determining potential cooperation enterprises, for the third type of enterprises, a relatively small number of enterprises (such as 3) are selected and contacted simultaneously in each round. Since this type of enterprise has had cooperation experience with enterprise A and the familiarity between the two sides is higher, a cooperation intention can be reached through relatively fewer communications or communications at a faster speed. Further, a relatively large number of enterprises with a preset quantity of cooperation intention are selected from the third type of enterprises. For example, according to the actual business scenario, the total number of the second type of second enterprises required is 8. Then, since the third type of enterprises can reach a cooperation intention faster, to improve the contact efficiency, 5 enterprises with the intention of cooperation are preset to be selected from this type of enterprises, and 3 enterprises with the intention of cooperation are preset to be selected from the fourth type of enterprises. It can be understood that in each round of communication process, 3 enterprises can be randomly selected for contact. After two rounds or more rounds, as long as the number of cooperation enterprises that reach the intention reaches the preset quantity of 5, the contact with the third type of enterprises will be stopped.

[0043] At the same time, for the fourth type of enterprises, a relatively large number of enterprises (such as 5) are selected and contacted simultaneously in each round. Because although this type of enterprise has had cooperation experience with enterprises similar to enterprise A, although they are similar enterprises, different enterprises still have some personalized requirements. Therefore, in order to quickly reach the preset quantity of potential cooperation enterprises (such as 3), a relatively large number of enterprises are selected and contacted simultaneously in each round. As mentioned above, and a relatively small number of enterprises with a preset quantity of cooperation intention (such as 3) are selected. Similarly, in each round of communication process, 5 enterprises can be randomly selected for contact. After multiple rounds of contact, as long as the number of cooperation enterprises that reach the intention reaches the preset quantity of 3, the contact with this fourth type of enterprises will be stopped.

[0044] Finally, the enterprise determines the final cooperation enterprises from the cooperation enterprises that reach the intention based on the contact situation.

[0045] Through this embodiment, first of all, this method analyzes the first needs of the enterprise, intelligently screens the candidate enterprise pool that meets this need, and performs hierarchical processing according to the importance of the needs. For the core needs, relatively few candidate enterprises are matched to ensure quality and supply chain stability while improving contact efficiency. For non-core needs, relatively more candidate enterprises are matched. These enterprises all have certain industry experience, either have had cooperation experience with the enterprise that puts forward the needs, or have had cooperation experience with enterprises similar to the enterprise that puts forward the needs. A relatively large number of enterprises with the intention of cooperation are selected from the enterprises that have had cooperation experience with the enterprise to ensure cost performance and rich supply chain, and at the same time improve contact efficiency; compared with the traditional enterprise contact method that usually relies on manual screening or simple rule matching, this method can improve the initiative of enterprise contact, meet the personalized needs of enterprise contact and reduce costs and increase efficiency.

[0046] A method for actively constructing enterprise - to - enterprise connections based on artificial intelligence corresponding to the above - mentioned embodiments Figure 2 The structural block diagram of a system for actively constructing enterprise - to - enterprise connections based on artificial intelligence provided by an embodiment of the present application is shown. For the sake of convenience, only the parts related to the embodiments of the present application are shown.

[0047] See Figure 2 As shown, a system 200 for actively constructing enterprise - to - enterprise connections based on artificial intelligence provided by an embodiment of the present application includes: a first acquisition module, configured to acquire a candidate second - enterprise pool that meets the first demand at least based on the first demand of the first enterprise initiating the connection; a first determination module, configured to determine the number and priority of the second enterprises to be contacted in the candidate second - enterprise pool; wherein, the first demand includes a first - type sub - demand and a second - type sub - demand, a first number of second enterprises of the first type are determined based on the first - type sub - demand, and a second number of second enterprises of the second type are determined based on the second - type sub - demand; wherein, the importance level of the first - type sub - demand is higher than that of the second - type sub - demand, and the first number is less than the second number; a connection - establishment module, configured to actively establish a connection between the first enterprise and the second enterprises based on the determined number and priority of the second enterprises to be contacted, and determine the intended cooperation enterprises based on the connection situation.

[0048] In some embodiments, the system 200 further includes that the first acquisition module is further configured to input the first demand into a pre - trained deep - learning model, and acquire a candidate second - enterprise pool that meets the first demand based on the output of the pre - trained deep - learning model.

[0049] In some embodiments, the system 200 further includes that the connection - establishment module is configured to actively establish connections with one or more of the first number of second enterprises of the first type for the first enterprise, and regard all of the first number of second enterprises of the first type as the intended cooperation enterprises.

[0050] In some embodiments, the system 200 further includes the establishing connection module, which is configured to classify the second type of second enterprises with the second quantity into two categories, namely the third type of enterprises and the fourth type of enterprises. Among them, the third type of enterprises are those that have a cooperation history with the first enterprise, and the fourth type of enterprises are those that have a cooperation history with the third enterprise similar to the first enterprise. For the third type of enterprises, the first enterprise proactively establishes connections with the third preset quantity of the third type of enterprises at one or more times, and takes the fourth preset quantity of the enterprises as the intended cooperation enterprises. For the fourth type of enterprises, the first enterprise proactively establishes connections with the fifth preset quantity of the fourth type of enterprises at one or more times, and takes the sixth preset quantity of the enterprises as the intended cooperation enterprises. Among them, the third preset quantity is less than the fifth preset quantity, and the fourth preset quantity is greater than the sixth preset quantity.

[0051] For the specific implementation of each of the above operations, reference may be made to the foregoing embodiments, which will not be elaborated herein.

[0052] Correspondingly, an embodiment of the present application further provides an electronic device, which may be a mobile terminal or a server. As Figure 3 shown, Figure 3 is a schematic structural diagram of the electronic device provided by the embodiment of the present application. For the sake of convenience of description, only the parts related to the embodiment of the present application are shown.

[0053] The electronic device 300 includes a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, and a computer program stored on the memory 302 and executable on the processor. Among them, the processor 301 is electrically connected to the memory 302. Those skilled in the art can understand that the structural diagram of the electronic device shown in the figure does not constitute a limitation on the electronic device, and it may include more or fewer components than shown in the figure, or combine certain components, or arrange different components.

[0054] The processor 301 is the control center of the electronic device 300, connecting various parts of the entire electronic device 300 through various interfaces and lines. By running or loading the software program (computer program) and / or unit stored in the memory 302, and calling the data stored in the memory 302, it executes various functions of the electronic device 300 and processes data, thereby monitoring the entire electronic device 300.

[0055] In an embodiment of the present application, the processor 301 in the electronic device 300 will load instructions corresponding to the processes of one or more application programs into the memory 302 according to the following steps, and the processor 301 will run the application programs stored in the memory 302 to implement various functions: obtaining a candidate second enterprise pool that meets the first requirements at least based on the first requirements of the first enterprise initiating the contact; determining the number and priority of the second enterprises to be contacted in the candidate second enterprise pool; wherein, the first requirements include first-type sub-requirements and second-type sub-requirements, determining a first number of second enterprises of the first type based on the first-type sub-requirements, and determining a second number of second enterprises of the second type based on the second-type sub-requirements; wherein, the importance level of the first-type sub-requirements is higher than that of the second-type sub-requirements, and the first number is less than the second number; actively establishing a connection between the first enterprise and the second enterprises based on the determined number and priority of the second enterprises to be contacted, and determining the intended cooperation enterprises based on the connection situation.

[0056] For the specific implementation of each of the above operations, reference may be made to the foregoing embodiments, which will not be elaborated herein.

[0057] Optionally, as Figure 3 shown, the electronic device 300 further includes: a contact actively constructing unit 303, a communication unit 304, an input unit 305, and a power supply 306. Among them, the processor 301 is electrically connected to the contact actively constructing unit 303, the communication unit 304, the input unit 305, and the power supply 306 respectively. Those skilled in the art can understand that Figure 3 the structure of the electronic device shown in

[0058] does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0059] The contact actively constructing unit 303 can be used for actively constructing contacts between enterprises based on artificial intelligence.

[0060] The communication unit 304 can be used for communicating with other devices.

[0061] The power supply 306 is used to supply power to each component of the electronic device 300. Optionally, the power supply 306 can be logically connected to the processor 301 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 306 can also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0062] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0063] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling relevant hardware through instructions. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0064] Therefore, an embodiment of the present application provides a computer-readable storage medium, in which multiple computer programs are stored. The computer programs can be loaded by a processor to execute the steps of an active construction method for enterprise-to-enterprise connections based on artificial intelligence provided by an embodiment of the present application.

[0065] For the specific implementation of the above operations, reference can be made to the previous embodiments, which will not be elaborated here.

[0066] Among them, the computer-readable storage medium can include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, etc.

[0067] Since the computer programs stored in the storage medium can execute the steps in any of the active construction methods for enterprise-to-enterprise connections based on artificial intelligence provided by the embodiments of the present application, the beneficial effects of any of the active construction methods for enterprise-to-enterprise connections based on artificial intelligence provided by the embodiments of the present application can be achieved. For details, reference can be made to the previous embodiments, which will not be elaborated here.

[0068] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0069] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to work in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more of the processes Figure 1 or sub-processes and / or boxes Figure 1 or sub-boxes.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes Figure 1 or sub-processes and / or boxes Figure 1 or sub-boxes.

[0071] The embodiments of the present invention have been described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the described embodiments. For those skilled in the art, without departing from the principles and spirit of the present invention, various changes, modifications, substitutions, and variations to these embodiments still fall within the protection scope of the present invention.

Claims

1. An active construction method for inter-enterprise connections based on artificial intelligence, characterized in that, Including: Obtaining a candidate second enterprise pool that meets the first demand based at least on the first demand of the first enterprise initiating the contact; Determining the quantity and priority of the second enterprises to be contacted in the candidate second enterprise pool; wherein, the first demand includes a first type of sub-demand and a second type of sub-demand, determining a first quantity of second enterprises of the first type based on the first type of sub-demand, and determining a second quantity of second enterprises of the second type based on the second type of sub-demand; wherein, the importance degree of the first type of sub-demand is higher than that of the second type of sub-demand, and the first quantity is less than the second quantity; based on the determined quantity and priority of the second enterprises to be contacted, actively establishing a connection between the first enterprise and the second enterprises and determining the intended cooperation enterprises based on the connection situation.

2. The active construction method for enterprise - to - enterprise connections based on artificial intelligence according to claim 1, wherein, The obtaining a candidate second enterprise pool that meets the first demand based at least on the first demand of the first enterprise initiating the contact includes inputting the first demand into a pre-trained deep learning model, and obtaining a candidate second enterprise pool that meets the first demand based on the output of the pre-trained deep learning model.

3. The active construction method for enterprise - to - enterprise connections based on artificial intelligence according to claim 1, characterized in that The actively establishing a connection between the first enterprise and the second enterprises and determining the intended cooperation enterprises based on the connection situation includes the first enterprise actively establishing connections with one or more of the first quantity of second enterprises of the first type at the same time, and taking all of the first quantity of second enterprises of the first type as the intended cooperation enterprises.

4. The active construction method of enterprise - to - enterprise connection based on artificial intelligence according to claim 3, characterized in that, The actively establishing a connection between the first enterprise and the second enterprises and determining the intended cooperation enterprises based on the connection situation includes dividing the second quantity of second enterprises of the second type into two categories, namely the third type of enterprises and the fourth type of enterprises, where the third type of enterprises are the enterprises that have a cooperation history with the first enterprise, and the fourth type of enterprises are the enterprises that have a cooperation history with a third enterprise similar to the first enterprise. For the third type of enterprises, the first enterprise actively establishes connections with a third preset quantity of the third type of enterprises at one time or multiple times, and takes a fourth preset quantity of the enterprises as the intended cooperation enterprises. For the fourth type of enterprises, the first enterprise actively establishes connections with a fifth preset quantity of the fourth type of enterprises at one time or multiple times, and takes a sixth preset quantity of the enterprises as the intended cooperation enterprises, where the third preset quantity is less than the fifth preset quantity, and the fourth preset quantity is greater than the sixth preset quantity.

5. An active construction system for enterprise - to - enterprise connections based on artificial intelligence, characterized in that, Including: A first obtaining module, configured to obtain a candidate second enterprise pool that meets the first demand based at least on the first demand of the first enterprise initiating the contact; A first determination module, configured to determine the number and priority of the second enterprises to be contacted in the candidate second enterprise pool; wherein, the first requirement includes a first type of sub-requirement and a second type of sub-requirement, a first number of second enterprises of the first type are determined based on the first type of sub-requirement, and a second number of second enterprises of the second type are determined based on the second type of sub-requirement; wherein, the importance degree of the first type of sub-requirement is higher than that of the second type of sub-requirement, and the first number is less than the second number; a connection establishment module, configured to actively establish a connection between the first enterprise and the second enterprise based on the determined number and priority of the second enterprises to be contacted, and determine the intended cooperation enterprises based on the connection situation.

6. An active construction system for enterprise - to - enterprise connections based on artificial intelligence according to claim 5, characterized in that, Including: The first acquisition module is further configured to input the first requirement into a pre-trained deep learning model, and based on the pre-trained deep learning model, output a candidate second enterprise pool that meets the first requirement.

7. An active construction system for enterprise - to - enterprise connections based on artificial intelligence according to claim 5, characterized in that, Including: The connection establishment module is configured to actively establish connections with one or more of the first number of second enterprises of the first type by the first enterprise, and regard all of the first number of second enterprises of the first type as the intended cooperation enterprises.

8. An active construction system for enterprise - to - enterprise connections based on artificial intelligence according to claim 7, characterized in that, Including: The connection establishment module is configured to divide the second number of second enterprises of the second type into two categories, namely the third type of enterprises and the fourth type of enterprises, wherein the third type of enterprises are the enterprises that have a cooperation history with the first enterprise, and the fourth type of enterprises are the enterprises that have a cooperation history with the third enterprises similar to the first enterprise. For the third type of enterprises, the first enterprise actively establishes connections with a third preset number of the third type of enterprises at one time or multiple times, and regards a fourth preset number of the enterprises as the intended cooperation enterprises. For the fourth type of enterprises, the first enterprise actively establishes connections with a fifth preset number of the fourth type of enterprises at one time or multiple times, and regards a sixth preset number of the enterprises as the intended cooperation enterprises. Among them, the third preset number is less than the fifth preset number, and the fourth preset number is greater than the sixth preset number.

9. A computer-readable storage medium storing a computer program, characterized in that: The computer program, when run by a processor, executes the method according to any one of claims 1-4.

10. An electronic device, characterized in that: Including a memory storing executable program code and a processor coupled to the memory; wherein, the processor calls the executable program code stored in the memory and executes the method according to any one of claims 1-4.

Images