Business opportunity recommendation method, device and equipment

Abstract

The invention discloses a business opportunity recommendation method, device and equipment, and relates to the technical field of data processing, and the method comprises the steps: carrying out the text information extraction of each piece of bidding and tendering data in a bidding and tendering data set, and taking an entry extracted from each piece of bidding and tendering data as first key information; performing text information extraction on the target enterprise information, and taking an entry extracted from the target enterprise information as second key information; performing industry classification on the first key information and the second key information; an improved TF-IDF algorithm is adopted to map the first key information and the corresponding industry category into a first word vector, and the second key information and the corresponding industry category are mapped into a second word vector; the word frequency in the improved TF-IDF algorithm is the word frequency based on industry category weight statistics; and calculating the cosine similarity of each first word vector and the second word vector, and determining business opportunity information according to each cosine similarity. The business opportunity recommendation accuracy is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a business opportunity recommendation method, device and equipment. Background Art

[0002] Business Intelligence (BI), also known as business wisdom or BI, is a system that integrates a variety of advanced technologies. It helps enterprises gain insight into market trends and optimize decision-making processes by collecting, storing, analyzing and displaying data inside and outside the enterprise. The BI system uses data warehouses to centrally manage data, uses online analytical processing (OLAP) technology to quickly access and analyze data, uses data mining technology to discover potential patterns and associations in data, and finally uses data visualization technology to present the analysis results to users in an intuitive and easy-to-understand way. In this way, enterprise decision makers can make more informed business decisions based on these analysis results.

[0003] At present, artificial intelligence (AI) processes complex nonlinear relationships between data through model training, and applies the trained models to actual business scenarios, so that the models can process real-time data and make predictions. However, the existing prediction modules for business opportunity decisions rely heavily on the quality and quantity of input data, which sometimes causes the models to be too complex (overfitting) or too simple (underfitting), thereby affecting the accuracy of data prediction. Therefore, there is an urgent need for a decision-making method in the case of low-quality data. Summary of the invention

[0004] The purpose of this application is to provide a business opportunity recommendation method, device and equipment, which can improve the accuracy of business opportunity recommendation when the data is of low quality.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a business opportunity recommendation method, the business opportunity recommendation method comprising:

[0007] Extract text information from each bidding data in the bidding data set, and use the terms extracted from each bidding data as the first key information;

[0008] Extract text information from the target enterprise information, and use the terms extracted from the target enterprise information as the second key information;

[0009] Classify each of the first key information and the second key information by industry; each of the first key information and the second key information corresponds to at least one industry category;

[0010] Using an improved TF-IDF algorithm, each of the first key information and the corresponding industry category is mapped into a first word vector, and the second key information and the corresponding industry category is mapped into a second word vector; the word frequency in the improved TF-IDF algorithm is a word frequency based on industry category weight statistics;

[0011] The cosine similarity between each first word vector and the second word vector is calculated, and the business opportunity information is determined according to each cosine similarity.

[0012] Optionally, using an improved TF-IDF algorithm to map each of the first key information and the corresponding industry category into a first word vector, and mapping the second key information and the corresponding industry category into a second word vector, specifically includes:

[0013] The importance score of each term is calculated using the formula WTF-IDF(w,λ,t,d,n,D)=WTF(w,λ,t,d,n)×IDF(t,D); each element in the first word vector is the importance score of each term in the first key information, and each element in the second word vector is the importance score of each term in the second key information;

[0014] Where, WTF-IDF(w,λ,t,d,n,D) is the importance score of term t in document d in document set D, WTF(w,λ,t,d,n) is the word frequency of term t in document d based on industry category weight statistics, and IDF(t,D) is the general importance of term t in document set D;

[0015]

[0016]

[0017] Among them, w is the industry weight, λ is a constant, n is the number of industry categories, and w i is the weight of industry category i, L i is the identifier of industry category i, L i =1 means that the entry t belongs to industry category i, L i = 0 means that the term t does not belong to industry category i, p(x i ) represents the probability of selecting industry category i; when calculating the importance scores of each term of the first key information, the document set D is the bidding data set; when calculating the importance scores of each term of the second key information, the document set D is the target enterprise information; st represents the constraint condition.

[0018] Optionally, the general importance of term t in the document set D is expressed as:

[0019] Optionally, text information is extracted from each piece of bidding data in the bidding data set, and the terms extracted from each piece of bidding data are used as the first key information, specifically including:

[0020] A large language model is used to extract text information from each bidding data in the bidding data set, and the terms extracted from each bidding data are used as the first key information.

[0021] Optionally, text information is extracted from the target enterprise information, and the terms extracted from the target enterprise information are used as the second key information, specifically including:

[0022] A large language model is used to extract text information from the target enterprise information, and the terms extracted from the target enterprise information are used as the second key information.

[0023] Optionally, each of the first key information and the second key information is classified by industry, specifically including:

[0024] A zero-sample learning strategy is used to classify the first key information and the second key information into different industries.

[0025] Optionally, determining the business opportunity information according to each cosine similarity specifically includes: taking the bidding data corresponding to the cosine similarity greater than a set value as the business opportunity information.

[0026] Optionally, the industry categories include education, medical care, media and tourism.

[0027] In a second aspect, the present application provides a business opportunity recommendation device, the business opportunity recommendation device comprising:

[0028] A first feature extraction module is used to extract text information from each bidding data in the bidding data set, and use the terms extracted from each bidding data as the first key information;

[0029] The second feature extraction module is used to extract text information from the target enterprise information and use the terms extracted from the target enterprise information as the second key information;

[0030] An industry classification module, used to classify each of the first key information and the second key information by industry; each of the first key information and the second key information corresponds to at least one industry category;

[0031] A word vector determination module, using an improved TF-IDF algorithm to map each of the first key information and the corresponding industry category into a first word vector, and to map the second key information and the corresponding industry category into a second word vector; the word frequency in the improved TF-IDF algorithm is a word frequency based on industry category weight statistics;

[0032] The business opportunity information output module is used to calculate the cosine similarity between each first word vector and the second word vector, and determine the business opportunity information according to each cosine similarity.

[0033] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the above-mentioned business opportunity recommendation methods.

[0034] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0035] The present application provides a business opportunity recommendation method, device and equipment, which calculates the cosine similarity between each first word vector and the second word vector, determines the business opportunity information according to each cosine similarity, overcomes the problem that a large amount of data is required for data prediction using a prediction model, and can improve the accuracy of business opportunity recommendation when the data is of low quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 This is an application environment diagram of a business opportunity recommendation method in an embodiment of the present application;

[0038] Figure 2 A flowchart of a business opportunity recommendation method provided in one embodiment of the present application;

[0039] Figure 3 A schematic diagram of functional modules of a business opportunity recommendation device provided in one embodiment of the present application;

[0040] Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0042] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0043] The business opportunity recommendation method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the bidding data to be processed and the target enterprise information to the server 104. After receiving the bidding data to be processed and the target enterprise information, the server 104 extracts text information from each bidding data in the bidding data set, and uses the terms extracted from each bidding data as the first key information; extracts text information from the target enterprise information, and uses the terms extracted from the target enterprise information as the second key information; classifies each of the first key information and the second key information into industries; each of the first key information and the second key information corresponds to at least one industry category; uses an improved TF-IDF algorithm to map each of the first key information and the corresponding industry category into a first word vector, and maps the second key information and the corresponding industry category into a second word vector; the word frequency in the improved TF-IDF algorithm is a word frequency based on industry category weight statistics; calculates the cosine similarity between each first word vector and the second word vector, and determines the business opportunity information according to each cosine similarity. The server 104 can feed back the obtained business opportunity information for the bidding data and the target enterprise information to the terminal 102. In addition, in some embodiments, the business opportunity recommendation method can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly recommend business opportunities for the bidding data and target enterprise information to be processed, or the server 104 can obtain the bidding data and target enterprise information to be processed from the data storage system and recommend business opportunities for the bidding data and target enterprise information to be processed.

[0044] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart TVs, smart car devices, etc. The portable wearable devices may be smart watches, smart bracelets, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0045] In an exemplary embodiment, Figure 2As shown, a business opportunity recommendation method is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 201 to 208.

[0046] Step 201: extract text information from each piece of bidding data in the bidding data set, and use the terms extracted from each piece of bidding data as the first key information.

[0047] Step 202: extract text information from the target enterprise information, and use the terms extracted from the target enterprise information as the second key information.

[0048] Step 203: Classify each of the first key information and the second key information by industry; each of the first key information and the second key information corresponds to at least one industry category.

[0049] Step 204: Use an improved TF-IDF algorithm to map each of the first key information and the corresponding industry category into a first word vector, and map the second key information and the corresponding industry category into a second word vector; the word frequency in the improved TF-IDF algorithm is a word frequency based on industry category weight statistics.

[0050] Step 205: Calculate the cosine similarity between each first word vector and the second word vector, and determine the business opportunity information according to each cosine similarity.

[0051] By calculating the cosine similarity between each first word vector and the second word vector, and determining the business opportunity information according to each cosine similarity, the problem that a large amount of data is required for data prediction using a prediction model is overcome, and the accuracy of business opportunity recommendations can be improved when the data is of low quality.

[0052] In addition, step 201 specifically includes: using a large language model (LLM) to extract text information from each bidding data in the bidding data set, and using the terms extracted from each bidding data as the first key information.

[0053] Each entry extracted from the bidding data constitutes a first key information.

[0054] The bidding data set contains bidding data from multiple channels, including historical bidding data and basic information data of customer channel merchants.

[0055] Among them, step 202 specifically includes: using a large language model to extract text information from the target enterprise information, and using the terms extracted from the target enterprise information as the second key information.

[0056] This application utilizes the ability of a large language model to extract key text information and extracts key information from bidding data and target enterprise information.

[0057] Before extracting text information from each bidding data or target enterprise information, the large language model first performs data cleaning and then extracts text information from the cleaned data.

[0058] Among them, step 203 specifically includes: using a zero-shot learning strategy to classify the first key information and the second key information into different industries.

[0059] The industry categories include education, medical care, media, tourism and many other industries.

[0060] This application uses an improved TF-IDF algorithm to map keywords and industry categories into a vector. The vectors mapped to each keyword and industry category constitute a vector space. Each dimension in the vector space corresponds to an entry, and the value of each dimension corresponds to the improved TF-IDF score of the entry. The keyword is an entry in the first key information or the second key information. The improved TF-IDF technology is used to map keywords and industry categories into a vector, and multiple discrete product industry terms are converted into a continuous vector space representation.

[0061] Wherein, step 204 specifically includes:

[0062] The formula WTF-IDF(w,λ,t,d,n,D)=WTF(w,λ,t,d,n)×IDF(t,D) is used to calculate the importance score of each term; each element in the first word vector is the importance score of each term in the first key information, and each element in the second word vector is the importance score of each term in the second key information (improved TF-IDF score).

[0063] Wherein, WTF-IDF(w,λ,t,d,n,D) is the importance score of term t in document d in document set D, WTF(w,λ,t,d,n) is the word frequency of term t in document d based on industry category weight statistics, and IDF(t,D) is the general importance of term t in document set D.

[0064]

[0065]

[0066] Among them, w is the industry weight, λ is a constant, n is the number of industry categories, and w i is the weight of industry category i, L i is the identifier of industry category i, L i =1 means that the entry t belongs to industry category i, L i = 0 means that the term t does not belong to industry category i, p(x i ) represents the probability of selecting industry category i, x i is the i-th value in the random variable; when calculating the importance scores of each term of the first key information, the document set D is the bidding data set; when calculating the importance scores of each term of the second key information, the document set D is the target enterprise information; st represents the constraint condition. It is an industry information item. The information entropy of the industry. This application takes into account the industry information items to reduce the entry score of the original information, reflecting the impact of industry categories on the importance of entries.

[0067] The weight of industry category i is determined according to the characteristics of the target enterprise, taking into account that the target enterprise has different product information in different industries, which significantly improves the accuracy.

[0068] Information entropy is an indicator that measures the uncertainty of random variables. The calculation formula is:

[0069] Where H(X) is the entropy of the random variable X, N is the number of possible values ​​of the random variable X, and p(x i ) represents the probability of the random variable X taking the i-th value.

[0070] Among them, λ can be regarded as an additional variable and can be determined by optimization. λ is generally a constant greater than 1. It is a penalty term, reflecting the L1 regularization method, which is used to compress the weights of some unimportant industries to 0.

[0071] L1 regularization, also known as Lasso regularization, is a technique used to prevent overfitting of machine learning models. Mathematically, it is usually implemented by adding a regularization term to the loss function, which is the sum of the absolute values ​​of the model parameters. In optimization problems, L1 regularization can be written in the form of constraints.

[0072] The general importance of term t in document set D is expressed as:

[0073] The second word vector corresponding to the target enterprise information is expressed as: A = [a1, a2, a3, ....., a n1-k ,a n1-k+1,....,a n1 ]. A is the second word vector, a p is the score of the term in the second word vector, 0≤p≤n1, where n1 is the sum of the number of terms and the number of industries.

[0074] Each piece of bidding data in the bidding data set corresponds to a first word vector.

[0075] Each first word vector is represented as: B = [b1, b2, b3, ....., b n1-k ,b n1-k+1 ,....,b n1 ], b q is the score of the term in the first word vector, 0≤q≤n1.

[0076] Wherein, determining the business opportunity information according to each cosine similarity in step 205 specifically includes: taking the bidding data corresponding to the cosine similarity greater than a set value as the business opportunity information.

[0077] The calculation formula for cosine similarity is: CS(A,B) is the cosine similarity between A and B.

[0078] This application integrates zero-shot technology and improved TF-IDF technology to convert each bidding data and target enterprise information in the bidding data set into a feature vector, and calculates the business opportunity data of the target enterprise through the cosine similarity formula.

[0079] Based on the same inventive concept, the embodiment of the present application also provides a business opportunity recommendation device for implementing the business opportunity recommendation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more business opportunity recommendation device embodiments provided below can refer to the limitations of the business opportunity recommendation method above, and will not be repeated here.

[0080] In an exemplary embodiment, Figure 3 As shown, a business opportunity recommendation device is provided, comprising:

[0081] The first feature extraction module is used to extract text information from each bidding data in the bidding data set, and use the terms extracted from each bidding data as the first key information.

[0082] The second feature extraction module is used to extract text information from the target enterprise information and use the terms extracted from the target enterprise information as the second key information.

[0083] An industry classification module is used to classify each of the first key information and the second key information by industry; each of the first key information and the second key information corresponds to at least one industry category.

[0084] The word vector determination module uses an improved TF-IDF algorithm to map each of the first key information and the corresponding industry category into a first word vector, and maps the second key information and the corresponding industry category into a second word vector; the word frequency in the improved TF-IDF algorithm is a word frequency based on industry category weight statistics.

[0085] The business opportunity information output module is used to calculate the cosine similarity between each first word vector and the second word vector, and determine the business opportunity information according to each cosine similarity.

[0086] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store business opportunity recommendation data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a business opportunity recommendation method is implemented.

[0087] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0088] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0089] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0090] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0091] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0092] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a data processing logic of a programmable logic device, etc., but is not limited thereto.

[0093] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0094] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A business opportunity recommendation method, characterized in that: The business opportunity recommendation method comprises: Extract text information from each bidding data in the bidding data set, and use the terms extracted from each bidding data as the first key information; Extract text information from the target enterprise information, and use the terms extracted from the target enterprise information as the second key information; Classify each of the first key information and the second key information by industry; each of the first key information and the second key information corresponds to at least one industry category; Using an improved TF-IDF algorithm, each of the first key information and the corresponding industry category is mapped into a first word vector, and the second key information and the corresponding industry category is mapped into a second word vector; the word frequency in the improved TF-IDF algorithm is a word frequency based on industry category weight statistics; The cosine similarity between each first word vector and the second word vector is calculated, and the business opportunity information is determined according to each cosine similarity.

2. The business opportunity recommendation method according to claim 1, characterized in that: The improved TF-IDF algorithm is used to map each of the first key information and the corresponding industry category into a first word vector, and the second key information and the corresponding industry category into a second word vector, specifically including: The importance score of each term is calculated using the formula WTF-IDF(w,λ,t,d,n,D)=WTF(w,λ,t,d,n)×IDF(t,D); each element in the first word vector is the importance score of each term in the first key information, and each element in the second word vector is the importance score of each term in the second key information; Where, WTF-IDF(w,λ,t,d,n,D) is the importance score of term t in document d in document set D, WTF(w,λ,t,d,n) is the word frequency of term t in document d based on industry category weight statistics, and IDF(t,D) is the general importance of term t in document set D; Among them, w is the industry weight, λ is a constant, n is the number of industry categories, and w i is the weight of industry category i, L i is the identifier of industry category i, L i =1 means that the entry t belongs to industry category i, L i = 0 means that the term t does not belong to industry category i, p(x i ) represents the probability of selecting industry category i; when calculating the importance scores of each term of the first key information, the document set D is the bidding data set; when calculating the importance scores of each term of the second key information, the document set D is the target enterprise information; st represents the constraint condition.

3. The business opportunity recommendation method according to claim 2, characterized in that: The general importance of term t in document set D is expressed as:

4. The business opportunity recommendation method according to claim 1, characterized in that: Extract text information from each bidding data in the bidding data set, and use the terms extracted from each bidding data as the first key information, including: A large language model is used to extract text information from each bidding data in the bidding data set, and the terms extracted from each bidding data are used as the first key information.

5. The business opportunity recommendation method according to claim 1, characterized in that: Extract text information from the target enterprise information, and use the terms extracted from the target enterprise information as the second key information, including: A large language model is used to extract text information from the target enterprise information, and the terms extracted from the target enterprise information are used as the second key information.

6. The business opportunity recommendation method according to claim 1, characterized in that: The first key information and the second key information are classified by industry, specifically including: A zero-sample learning strategy is used to classify the first key information and the second key information into different industries.

7. The business opportunity recommendation method according to claim 1, characterized in that: Determining business opportunity information according to each cosine similarity specifically includes: taking the bidding data corresponding to the cosine similarity greater than a set value as the business opportunity information.

8. The business opportunity recommendation method according to claim 1, characterized in that: The industry categories mentioned include education, medical care, media and tourism.

9. A business opportunity recommendation device, characterized in that: The business opportunity recommendation device comprises: A first feature extraction module is used to extract text information from each bidding data in the bidding data set, and use the terms extracted from each bidding data as the first key information; The second feature extraction module is used to extract text information from the target enterprise information and use the terms extracted from the target enterprise information as the second key information; An industry classification module, used to classify each of the first key information and the second key information by industry; each of the first key information and the second key information corresponds to at least one industry category; A word vector determination module, using an improved TF-IDF algorithm to map each of the first key information and the corresponding industry category into a first word vector, and to map the second key information and the corresponding industry category into a second word vector; the word frequency in the improved TF-IDF algorithm is a word frequency based on industry category weight statistics; The business opportunity information output module is used to calculate the cosine similarity between each first word vector and the second word vector, and determine the business opportunity information according to each cosine similarity.

10. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the business opportunity recommendation method according to any one of claims 1 to 8.

Images