Enterprise business model recommendation methods, devices, equipment and storage media

Abstract

This invention relates to the field of business model recommendation technology, and more particularly to a business model recommendation method, apparatus, device, and storage medium. The method first obtains multiple first entities; then, for each first entity, based on multiple attributes of the first entity, it determines multiple entities similar to the first entity from a knowledge graph as multiple second entities, constructing multiple second entity sets to obtain multiple second entity sets; next, from the multiple business model entities, it finds multiple business model entities that are connected to entities in the multiple second entity sets through business model attributes, as multiple third entities; finally, based on the similarity between the second and first entities, the number of attributes connecting the second entities to the third entities, and the proportion of the third entities in all business model entities, it selects business model entities from the multiple third entities for recommendation. This invention eliminates the need to consult relevant regulations and standards, is simpler to operate, and improves the efficiency of business model selection.

Description

Technical Field

[0001] This invention relates to the field of enterprise business model recommendation technology, and in particular to a method, apparatus, device and storage medium for enterprise business model recommendation based on knowledge graph. Background Technology

[0002] In layman's terms, a knowledge graph is a relational network that connects all kinds of heterogeneous information. A knowledge graph consists of nodes and edges. Each node represents an "entity" that exists in the real world, and each edge represents a "relationship" between entities. Knowledge graphs are the most efficient way to represent relationships.

[0003] When knowledge graphs are applied to enterprises, they make it easier for businesses to identify relationships and extract useful information. For example, adding a business model to a knowledge graph can make the business model's structure clearer and more visual.

[0004] In traditional technologies, when selecting a business model, operators need to refer to the company's regulations and standards. Even after the company's business model is incorporated into a knowledge graph, the selection method for the business model has not changed substantially, and the problems of cumbersome selection and easy misselection of business models still exist.

[0005] Therefore, it is necessary to develop and design a business model recommendation method for enterprises. Summary of the Invention

[0006] The present invention provides a method, apparatus, device and storage medium for recommending enterprise business models, which solves the problem of the cumbersome selection of job business models in the prior art.

[0007] In a first aspect, embodiments of the present invention provide a method for recommending enterprise business models, including:

[0008] Obtain multiple first entities, where entities are connected to other entities through attributes to form a knowledge graph;

[0009] For each first entity, multiple entities similar to the first entity are determined from the knowledge graph based on multiple attributes of the first entity as multiple second entities, and the multiple second entities are constructed into a second entity set to obtain multiple second entity sets;

[0010] From multiple business model entities, identify multiple business model entities that are connected to entities in the multiple second entity sets through business model attributes, and use them as multiple third entities;

[0011] Based on the similarity between the second entity and the first entity, the number of attributes that the second entity connects to the third entity, and the proportion of the third entity in all business model entities, a business model entity is selected from the plurality of third entities for recommendation.

[0012] In one possible implementation, determining, for each first entity, multiple entities similar to the first entity from the knowledge graph as multiple second entities based on multiple attributes of the first entity includes:

[0013] For each first entity, perform the following steps:

[0014] Entities are extracted sequentially from the knowledge graph as entities to be processed;

[0015] The number of common attributes between the entity to be processed and the first entity is counted and used as the first quantity;

[0016] Calculate the ratio of the first quantity to the number of first entity attributes, and use this as the first ratio.

[0017] If the similarity value is greater than the first threshold, then the entity to be processed is regarded as the second entity, and the first ratio is regarded as the similarity between the second entity and the first entity;

[0018] Otherwise, if the traversal of the knowledge graph is not completed, the process jumps to the step of sequentially extracting entities from the knowledge graph as entities to be processed.

[0019] In one possible implementation, the step of selecting business model entities for recommendation from the plurality of third entities based on the similarity between the second entity and the first entity, the number of attributes connecting the second entity to the third entity, and the proportion of the third entity in all business model entities includes:

[0020] For each third entity, the connection frequencies between the multiple sets of second entities and the third entity are extracted based on the similarity between the second entity and the first entity, and the multiple connection frequencies are constructed into a connection frequency set, thereby obtaining multiple connection frequency sets. The connection frequency represents the frequency characteristics of the third entity connecting to the similar entities of the first entity. Each connection frequency set corresponds to a third entity, and each connection frequency in the connection frequency set corresponds to a second entity set.

[0021] For each second entity set, multiple third entities connected to the second entity set are selected from the multiple third entities as multiple second associated entities, and the multiple second associated entities are used to construct a second associated entity set, thereby obtaining multiple second entity sets;

[0022] Based on the number of entities in each second associated entity set and the total number of business model entities, a scarcity index is determined, thereby obtaining multiple scarcity indices. The scarcity index represents the scarcity of the third entities connected to the second entity set, and each scarcity index corresponds to a second entity set.

[0023] Based on the multiple connection frequency sets and the multiple scarcity indices, multiple matching degrees are determined, wherein the matching degree characterizes the degree of matching between the third entity and the multiple first entities;

[0024] Based on the multiple matching degrees, a business model entity is selected from the multiple third entities for recommendation.

[0025] In one possible implementation, the step of extracting the connection frequencies of the multiple sets of second entities connected to the third entity based on the similarity between the second entity and the first entity includes:

[0026] For each second entity set, perform the following steps:

[0027] Get and initialize the first accumulated sum;

[0028] Extract the second entities from the second entity set in sequence, and use them as the second entities to be processed;

[0029] Extract the similarity between the second entity to be processed and the corresponding first entity, and use it as the similarity to be processed;

[0030] Extract the number of connections between the second and third entities to be processed, and use this as the number of entities to be processed.

[0031] Calculate the product of the similarity to be processed and the number to be processed, as the entity frequency, where the entity frequency represents the frequency at which the second entity and the third entity to be processed are connected;

[0032] The entity frequency is added to the first sum, and the first sum is updated using the obtained sum;

[0033] If the second entity set has not been traversed, then proceed to the step of sequentially extracting the second entity from the second entity set as the second entity to be processed;

[0034] Otherwise, the ratio of the first accumulated sum to the number of attributes of the third entity to be processed is calculated as the target entity frequency, wherein the third entity to be processed is a third entity from the first attribute set.

[0035] In one possible implementation, determining the scarcity index based on the number of entities in each second associated entity set and the total number of business model entities includes:

[0036] The scarcity index is determined based on the first formula, the number of entities in each second associated entity set, and the total number of entities in all business models. The first formula is:

[0037]

[0038] In the formula, For the corresponding number The scarcity index of the third entity connected to a second entity set. As the base, The number of entities in all business models. This represents the number of entities in the second associated entity set.

[0039] In one possible implementation, determining the scarcity index based on the number of entities in each second associated entity set and the total number of business model entities includes:

[0040] For each second set of associated entities, perform the following steps:

[0041] Calculate the quotient between the number of all business model entities and the number of entities in the second associated entity set, round the quotient to the nearest integer and represent it in binary to obtain the data to be processed;

[0042] Take the rightmost data from the data to be processed and shift the data to the right.

[0043] Based on the second formula, the number of right shifts, and the rightmost data retrieved, update the second cumulative sum, where the second formula is:

[0044]

[0045] In the formula, This is the updated second cumulative sum. This is the second cumulative sum before the update. To retrieve the rightmost data, This represents the number of right shifts;

[0046] If the data to be processed has not been traversed completely, then proceed to the step of taking out the rightmost data from the data to be processed and shifting the data to be processed to the right;

[0047] Otherwise, the second summation is used as the scarcity index.

[0048] In one possible implementation, determining multiple matching degrees based on the multiple sets of connection frequencies and the multiple scarcity indices includes:

[0049] For each of the plurality of third entities, perform the following steps respectively:

[0050] Extract the set of connection frequencies corresponding to the third entity as the set of connection frequencies to be processed;

[0051] The matching degree is determined based on the third formula, the set of connection frequencies to be processed, and the multiple scarcity indices, wherein the third formula is:

[0052]

[0053] In the formula, For matching degree, For the connection frequencies to be processed, the corresponding number is... The connection frequency of the second entity set For the corresponding number The scarcity index of the third entity connected to a second entity set. This represents the total number of entities in the second entity set.

[0054] Secondly, embodiments of the present invention provide an enterprise business model recommendation apparatus for implementing the enterprise business model recommendation method as described in the first aspect or any possible implementation thereof, the enterprise business model recommendation apparatus comprising:

[0055] The keyword entity acquisition module is used to acquire multiple first entities, where entities are connected to other entities through attributes to form a knowledge graph;

[0056] The keyword expansion module is used to determine, for each first entity, multiple entities similar to the first entity from the knowledge graph based on multiple attributes of the first entity as multiple second entities, and construct the multiple second entities into a second entity set, thereby obtaining multiple second entity sets;

[0057] The business model entity search module is used to find multiple business model entities that are connected to entities in the multiple second entity sets through business model attributes from multiple business model entities, and to serve as multiple third entities.

[0058] as well as,

[0059] The enterprise business model recommendation module is used to select business model entities for recommendation from the plurality of third entities based on the similarity between the second entity and the first entity, the number of attributes of the second entity connected to the third entity, and the proportion of the third entity in all business model entities.

[0060] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor executes the computer program to implement the steps of the method as described in the first aspect or any possible implementation of the first aspect.

[0061] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in the first aspect or any possible implementation thereof.

[0062] The beneficial effects of the embodiments of the present invention compared with the prior art are:

[0063] This invention discloses a method for recommending enterprise business models. First, multiple first entities are obtained, where each entity is connected to other entities through attributes to form a knowledge graph. Then, for each first entity, multiple entities similar to the first entity are determined from the knowledge graph based on multiple attributes of the first entity, serving as multiple second entities. These multiple second entities are then constructed into a second entity set, resulting in multiple second entity sets. Next, from multiple business model entities, multiple business model entities connected to entities in the multiple second entity sets through business model attributes are identified, serving as multiple third entities. Finally, based on the similarity between the second and first entities, the number of attributes connecting the second entity to the third entities, and the proportion of the third entity in all business model entities, a business model entity is selected from the multiple third entities for recommendation. This invention finds multiple similar entities based on the first entities and, based on the scarcity of connections between similar entities and business model entities in the knowledge graph and the frequency of connections between similar entities in business model entities, finds suitable operational business models. Since the search only requires inputting entity keywords for matching, there is no need to consult relevant regulations and standards, making the operation simpler and improving the efficiency of business model selection. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 This is a flowchart of the enterprise business model recommendation method provided in the embodiments of the present invention;

[0066] Figure 2 This is a schematic diagram of the knowledge graph structure provided in the embodiments of the present invention;

[0067] Figure 3 This is a relationship diagram of the first entity, the second entity, and the third entity provided in the embodiments of the present invention;

[0068] Figure 4This is a schematic diagram of the connection frequency determination method provided by the embodiments of the present invention;

[0069] Figure 5 This is a functional block diagram of the enterprise business model recommendation device provided in the embodiments of the present invention;

[0070] Figure 6 This is a functional block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0071] In the following description, specific details such as particular system structures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0072] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0073] The embodiments of the present invention will be described in detail below. This example is implemented based on the technical solution of the present invention, and provides detailed implementation methods and specific operation processes. However, the protection scope of the present invention is not limited to the following embodiments.

[0074] Figure 1 A flowchart of an enterprise business model recommendation method provided for an embodiment of the present invention.

[0075] like Figure 1 As shown, it illustrates the implementation flowchart of the enterprise business model recommendation method provided by the embodiments of the present invention, which is described in detail below:

[0076] In step 101, multiple first entities are obtained, wherein the entities are connected to other entities through attributes to form a knowledge graph.

[0077] For example, the knowledge graph of the embodiments of the present invention is as follows: Figure 2As shown, entities are connected through attributes, and multiple first entities are keywords used to search for the target business model. For example, entity 201, Zhang San, is a company employee. This entity has multiple attributes and corresponding entities for these attributes. He wants to submit a car rental application, which involves many attributes, such as whether the vehicle is a truck or a bus, the number of seats, the purpose of the rental, the travel distance, and the number of goods or people carried. Zhang San inputs his name and car rental request as the keyword entity. The knowledge graph filtering system should find a suitable business model from the knowledge graph that matches the above keywords. In fact, the knowledge graph contains such an entity, which is connected to a business model entity 202 with similar attributes and similar or identical request attributes to entity Zhang San. We should filter out such a business model entity 202 from the knowledge graph and recommend this business model entity 202 and its attribute 203 to Zhang San.

[0078] The embodiment of this invention finds the most suitable business model by matching the aforementioned keywords. For example... Figure 3 As shown in the figure, this diagram illustrates the principle of constructing a second entity set 302 through a first entity 201, and determining multiple third entities 304 from multiple business model entities 303 through the second entity set 302. In this embodiment of the invention, a similar entity search is first performed on each keyword entity (first entity 201), and the found entities are designated as second entities. Based on the relationship between the second entities and the keyword entities, multiple second entities are constructed into a second entity set 302. Then, starting from the second entities, business model entities connected to the second entities are found, serving as multiple third entities 304. Then, by determining the frequency of connections between each third entity 305 and the second entity, as well as the scarcity of third entities 305 connected to the second entity set 302, recommended business model entities are found from the multiple third entities 304 and recommended.

[0079] To achieve the above objectives, embodiments of the present invention determine the frequency of the connection between the third entity and the second entity and the scarcity of the third entity through the following steps.

[0080] In step 102, for each first entity, multiple entities similar to the first entity are determined from the knowledge graph based on multiple attributes of the first entity as multiple second entities, and the multiple second entities are constructed into a second entity set to obtain multiple second entity sets.

[0081] In some embodiments, step 102 includes:

[0082] For each first entity, perform the following steps:

[0083] Entities are extracted sequentially from the knowledge graph as entities to be processed;

[0084] The number of common attributes between the entity to be processed and the first entity is counted and used as the first quantity;

[0085] Calculate the ratio of the first quantity to the number of first entity attributes, and use this as the first ratio.

[0086] If the similarity value is greater than the first threshold, then the entity to be processed is regarded as the second entity, and the first ratio is regarded as the similarity between the second entity and the first entity;

[0087] Otherwise, if the traversal of the knowledge graph is not completed, the process jumps to the step of sequentially extracting entities from the knowledge graph as entities to be processed.

[0088] For example, regarding the determination of the second entity, the embodiments of the present invention extract the attributes of each first entity and extract entities from the knowledge graph whose ratio of the number of attributes shared with the first entity exceeds a first threshold as the second entity. We can see that the purpose of setting the first threshold is to perform an initial screening of the entities extracted from the knowledge graph and to filter out those entities that are obviously not the target entities. Usually, the first threshold is set low to prevent over-screening (removing the target entities). In some application scenarios, the first threshold is set to below 0.3. Figure 2 Among them, Zhang San, as the first entity, shares many attributes with entity Li Si. Therefore, entity Li Si is selected as the second entity.

[0089] In addition, each second entity will have a similarity score calculated based on the number of shared attributes. This similarity score is typically the ratio of the number of shared attributes to the number of first entities. For example, Figure 2 In the example, entity Zhang San has six attributes, and it shares five attributes with entity Li Si. Therefore, the similarity between the two entities is 5 / 6.

[0090] In step 103, from the multiple business model entities, multiple business model entities that are connected to entities in the multiple second entity sets through business model attributes are identified as multiple third entities.

[0091] In step 104, a business model entity is selected from the plurality of third entities for recommendation based on the similarity between the second entity and the first entity, the number of attributes of the second entity connected to the third entity, and the proportion of the third entity in all business model entities.

[0092] In some embodiments, step 104 includes:

[0093] The step of selecting business model entities for recommendation from the plurality of third entities based on the similarity between the second entity and the first entity, the number of attributes of the second entity connected to the third entity, and the proportion of the third entity in all business model entities includes:

[0094] For each third entity, the connection frequencies between the multiple sets of second entities and the third entity are extracted based on the similarity between the second entity and the first entity, and the multiple connection frequencies are constructed into a connection frequency set, thereby obtaining multiple connection frequency sets. The connection frequency represents the frequency characteristics of the third entity connecting to the similar entities of the first entity. Each connection frequency set corresponds to a third entity, and each connection frequency in the connection frequency set corresponds to a second entity set.

[0095] For each second entity set, multiple third entities connected to the second entity set are selected from the multiple third entities as multiple second associated entities, and the multiple second associated entities are used to construct a second associated entity set, thereby obtaining multiple second entity sets;

[0096] Based on the number of entities in each second associated entity set and the total number of business model entities, a scarcity index is determined, thereby obtaining multiple scarcity indices. The scarcity index represents the scarcity of the third entities connected to the second entity set, and each scarcity index corresponds to a second entity set.

[0097] Based on the multiple connection frequency sets and the multiple scarcity indices, multiple matching degrees are determined, wherein the matching degree characterizes the degree of matching between the third entity and the multiple first entities;

[0098] Based on the multiple matching degrees, a business model entity is selected from the multiple third entities for recommendation.

[0099] In some implementations, the step of extracting the connection frequencies of the plurality of second entity sets respectively connected to the third entity based on the similarity between the second entity and the first entity includes:

[0100] For each second entity set, perform the following steps:

[0101] Get and initialize the first accumulated sum;

[0102] Extract the second entities from the second entity set in sequence, and treat them as the second entities to be processed;

[0103] Extract the similarity between the second entity to be processed and the corresponding first entity, and use it as the similarity to be processed;

[0104] Extract the number of connections between the second and third entities to be processed, and use this as the number of entities to be processed.

[0105] Calculate the product of the similarity to be processed and the number to be processed, as the entity frequency, where the entity frequency represents the frequency at which the second entity and the third entity to be processed are connected;

[0106] The entity frequency is added to the first sum, and the first sum is updated using the obtained sum;

[0107] If the second entity set has not been traversed, then proceed to the step of sequentially extracting the second entity from the second entity set as the second entity to be processed;

[0108] Otherwise, the ratio of the first accumulated sum to the number of attributes of the third entity to be processed is calculated as the target entity frequency, wherein the third entity to be processed is a third entity from the first attribute set.

[0109] In some implementations, determining the scarcity index based on the number of entities in each second associated entity set and the total number of business model entities includes:

[0110] The scarcity index is determined based on the first formula, the number of entities in each second associated entity set, and the total number of entities in all business models. The first formula is:

[0111]

[0112] In the formula, For the corresponding number The scarcity index of the third entity connected to a second entity set. As the base, The number of entities in all business models. This represents the number of entities in the second associated entity set.

[0113] In some implementations, determining the scarcity index based on the number of entities in each second associated entity set and the total number of business model entities includes:

[0114] For each second set of associated entities, perform the following steps:

[0115] Calculate the quotient between the number of all business model entities and the number of entities in the second associated entity set, round the quotient to the nearest integer and represent it in binary to obtain the data to be processed;

[0116] Take the rightmost data from the data to be processed and shift the data to the right.

[0117] Based on the second formula, the number of right shifts, and the rightmost data retrieved, update the second cumulative sum, where the second formula is:

[0118]

[0119] In the formula, This is the updated second cumulative sum. This is the second cumulative sum before the update. To retrieve the rightmost data, This represents the number of right shifts;

[0120] If the data to be processed has not been traversed completely, then proceed to the step of taking out the rightmost data from the data to be processed and shifting the data to the right.

[0121] Otherwise, the second summation is used as the scarcity index.

[0122] In some implementations, determining multiple matching degrees based on the plurality of connection frequency sets and the plurality of scarcity indices includes:

[0123] For each of the plurality of third entities, perform the following steps respectively:

[0124] Extract the set of connection frequencies corresponding to the third entity as the set of connection frequencies to be processed;

[0125] The matching degree is determined based on the third formula, the set of connection frequencies to be processed, and the multiple scarcity indices, wherein the third formula is:

[0126]

[0127] In the formula, For matching degree, For the connection frequencies to be processed, the corresponding number is... The connection frequency of the second entity set For the corresponding number The scarcity index of the third entity connected to a second entity set. This represents the total number of entities in the second entity set.

[0128] For example, as described above, the present invention makes enterprise business model recommendations by statistically analyzing the second connection frequency of each third entity and the scarcity of the third entity.

[0129] Regarding the connection frequency of the third entity, such as Figure 4As shown, each third entity 305 extracts connected entities from each second entity set 302 (a total of 3 in the figure), and extracts the similarity scores S1, S2, and S3 between these connected entities and their corresponding first entities. These similarity scores are then summed to obtain a cumulative value. The number of all attributes of this third entity 305 (a total of 6 in the figure) is then counted. Dividing the cumulative similarity value by the number of attributes yields the connection frequency of the third entity. This connection frequency reflects the degree of association between the third entity 305 and the second entity set 302, and also reflects the similarity between the second entity set 302 and the first entity 201. In other words, this connection frequency reflects the degree of association and similarity between the third entity 305 and the first entity 201. Since the third entity 305 has attribute connections with multiple second entity sets 302, each third entity 305 will have connection frequencies corresponding to multiple second entity sets 302. These connection frequencies are constructed into a connection frequency set.

[0130] The connection frequency set reflects the correlation and similarity between a third entity and multiple first entities. However, in reality, relying solely on the connection frequency set for recommendations is unreliable. For example, there are many business model entities with requester attributes, but fewer with driver attributes. Obviously, third entities with driver attributes should be given more attention because this attribute allows them to be quickly separated from other third entities. This characteristic is precisely the scarcity index of the embodiments of this invention.

[0131] For each second entity set, find all third entities connected to this entity set, and determine the scarcity index through the third entities and all business model entities. One way to do this is by using the first formula:

[0132]

[0133] In the formula, For the corresponding number The scarcity index of the third entity connected to a second entity set. As the base, The number of entities in all business models. This represents the number of entities in the second associated entity set.

[0134] In the above formula, the base should be a number greater than 1. As can be seen from the above formula, the scarcity index is positively correlated with the scarcity of the third entity connected to the second entity set. In other words, the scarcity is greater, the scarcity index is larger.

[0135] If almost all business model entities are connected to a certain second entity set, the scarcity index is 0, as shown in the above formula. However, when only a very few business model entities are connected to a certain second entity set, the scarcity index becomes a large number.

[0136] Furthermore, as can be seen from the above formula, the scarcity index actually reflects the probability that the second entity set, or the similar entities of the first entity, are connected in the business model entity. The number of scarcity indices is the same as the number of the second entity set, and they correspond one-to-one.

[0137] Since the embodiments of the present invention can be executed in a computer program, the present invention provides another method for determining scarcity. This method calculates the quotient of the total number of business model entities and the number of third entities connected to a certain second entity set. This quotient is integerized and represented in binary. Then, a right shift is initiated, and the accumulated sum is updated once using a second formula for each shift.

[0138]

[0139] In the formula, This is the updated second cumulative sum. This is the second cumulative sum before the update. To retrieve the rightmost data, This represents the number of right shifts.

[0140] After all data is shifted to the right, the sum is the scarcity index.

[0141] Based on the connection frequency set obtained from the aforementioned steps and the scarcity index corresponding to each second entity set, the third entity can determine its matching degree with multiple first entities. This embodiment of the invention utilizes a third formula to determine the matching degree:

[0142]

[0143] In the formula, For matching degree, For the connection frequencies to be processed, the corresponding number is... The connection frequency of the second entity set For the corresponding number The scarcity index of the third entity connected to a second entity set. This represents the total number of entities in the second entity set.

[0144] Clearly, third entities with higher matching degrees should be given priority in recommendations.

[0145] The present invention provides an implementation method for recommending enterprise business models. First, multiple first entities are obtained, where each entity is connected to other entities through attributes to form a knowledge graph. Then, for each first entity, multiple entities similar to the first entity are determined from the knowledge graph based on multiple attributes of the first entity, serving as multiple second entities. These multiple second entities are then constructed into a second entity set, resulting in multiple second entity sets. Next, from multiple business model entities, multiple business model entities connected to entities in the multiple second entity sets through business model attributes are identified, serving as multiple third entities. Finally, based on the similarity between the second and first entities, the number of attributes connecting the second entity to the third entities, and the proportion of the third entity in all business model entities, a business model entity is selected from the multiple third entities for recommendation. This implementation method finds multiple similar entities based on the first entities and, based on the scarcity of connections between similar entities and business model entities in the knowledge graph and the frequency of connections between similar entities in business model entities, finds suitable operational business models. Since the search only requires inputting entity keywords for matching, there is no need to consult relevant regulations and standards, making the operation simpler and improving the efficiency of business model selection.

[0146] The embodiments of the present invention construct a knowledge graph by digitizing and identifying entities, connecting entities with digital attributes, and finding suitable business models through entity matching, thereby improving the accuracy of enterprise business model recommendations.

[0147] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0148] The following are embodiments of the apparatus of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0149] Figure 5 This is a functional block diagram of the enterprise business model recommendation device provided in the embodiments of the present invention, with reference to... Figure 5 The enterprise business model recommendation device includes: a keyword entity acquisition module 501, a keyword expansion module 502, a business model entity search module 503, and an enterprise business model recommendation module 504, wherein:

[0150] Keyword entity acquisition module 501 is used to acquire multiple first entities, where entities are connected to other entities through attributes to form a knowledge graph;

[0151] The keyword expansion module 502 is used to determine, for each first entity, multiple entities similar to the first entity from the knowledge graph based on multiple attributes of the first entity as multiple second entities, and construct the multiple second entities into a second entity set, thereby obtaining multiple second entity sets;

[0152] The business model entity search module 503 is used to find multiple business model entities that are connected to entities in the multiple second entity sets through business model attributes from multiple business model entities, and to serve as multiple third entities.

[0153] The enterprise business model recommendation module 504 is used to select business model entities for recommendation from the plurality of third entities based on the similarity between the second entity and the first entity, the number of attributes of the second entity connected to the third entity, and the proportion of the third entity in all business model entities.

[0154] Figure 6 This is a functional block diagram of the electronic device provided in an embodiment of the present invention. For example... Figure 6 As shown, the electronic device 6 of this embodiment includes a processor 600 and a memory 601, wherein the memory 601 stores a computer program 602 that can run on the processor 600. When the processor 600 executes the computer program 602, it implements the steps of the various enterprise business model recommendation methods and embodiments described above, for example... Figure 1 Steps 101 to 104 are shown.

[0155] For example, the computer program 602 may be divided into one or more modules / units, which are stored in the memory 601 and executed by the processor 600 to complete the present invention.

[0156] The electronic device 6 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The electronic device 6 may include, but is not limited to, a processor 600 and a memory 601. Those skilled in the art will understand that... Figure 6 This is merely an example of electronic device 6 and does not constitute a limitation on electronic device 6. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 6 may also include input / output devices, network access devices, buses, etc.

[0157] The processor 600 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0158] The memory 601 can be an internal storage unit of the electronic device 6, such as a hard disk or memory. The memory 601 can also be an external storage device of the electronic device 6, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 601 can include both internal and external storage units of the electronic device 6. The memory 601 is used to store the computer program 602 and other programs and data required by the electronic device 6. The memory 601 can also be used to temporarily store data that has been output or will be output.

[0159] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the aforementioned method embodiments, and will not be repeated here.

[0160] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0161] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0162] In the embodiments provided by this invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0163] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0164] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0165] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-described embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various methods and apparatus embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0166] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A business model recommendation method for enterprises, characterized in that, include: Obtain multiple first entities, where entities are connected to other entities through attributes to form a knowledge graph, and the first entities are keywords used to search for target business models; For each first entity, multiple entities similar to the first entity are determined from the knowledge graph based on multiple attributes of the first entity as multiple second entities, and the multiple second entities are constructed into a second entity set to obtain multiple second entity sets; From multiple business model entities, find multiple business model entities that are connected to entities in the multiple second entity sets through business model attributes, and serve as multiple third entities. The business model includes an enterprise business description entity, multiple necessary attributes for carrying out enterprise business connected to the enterprise business description entity, and attribute entities connected to the necessary attributes. Based on the similarity between the second entity and the first entity, the number of attributes that the second entity connects to the third entity, and the proportion of the third entity in all business model entities, a business model entity is selected from the plurality of third entities for recommendation. The step of selecting business model entities for recommendation from the plurality of third entities based on the similarity between the second entity and the first entity, the number of attributes of the second entity connected to the third entity, and the proportion of the third entity in all business model entities includes: For each third entity, the connection frequencies between the multiple sets of second entities and the third entity are extracted based on the similarity between the second entity and the first entity, and the multiple connection frequencies are constructed into a connection frequency set, thereby obtaining multiple connection frequency sets. The connection frequency represents the frequency characteristics of the third entity connecting to the similar entities of the first entity. Each connection frequency set corresponds to a third entity, and each connection frequency in the connection frequency set corresponds to a second entity set. For each second entity set, multiple third entities connected to the second entity set are selected from the multiple third entities as multiple second associated entities, and the multiple second associated entities are used to construct a second associated entity set, thereby obtaining multiple second entity sets; Based on the number of entities in each second associated entity set and the total number of business model entities, a scarcity index is determined, thereby obtaining multiple scarcity indices. The scarcity index represents the scarcity of the third entities connected to the second entity set, and each scarcity index corresponds to a second entity set. Based on the multiple connection frequency sets and the multiple scarcity indices, multiple matching degrees are determined, wherein the matching degree characterizes the degree of matching between the third entity and the multiple first entities; Based on the multiple matching degrees, a business model entity is selected from the multiple third entities for recommendation; The step of extracting the connection frequencies of the multiple sets of second entities connected to the third entity based on the similarity between the second entity and the first entity includes: For each second entity set, perform the following steps: Get and initialize the first accumulated sum; Extract the second entities from the second entity set in sequence, and treat them as the second entities to be processed; Extract the similarity between the second entity to be processed and the corresponding first entity, and use it as the similarity to be processed; Extract the number of connections between the second and third entities to be processed, and use this as the number of entities to be processed. Calculate the product of the similarity to be processed and the number to be processed, as the entity frequency, where the entity frequency represents the frequency at which the second entity and the third entity to be processed are connected; The entity frequency is added to the first sum, and the first sum is updated using the obtained sum; If the second entity set has not been traversed, then proceed to the step of sequentially extracting the second entity from the second entity set as the second entity to be processed; Otherwise, the ratio of the first accumulated sum to the number of attributes of the third entity to be processed is calculated as the target entity frequency, wherein the third entity to be processed is a third entity from the first attribute set.

2. The enterprise business model recommendation method according to claim 1, characterized in that, For each first entity, determining multiple entities similar to the first entity from the knowledge graph based on multiple attributes of the first entity as multiple second entities includes: For each first entity, perform the following steps: Entities are extracted sequentially from the knowledge graph as entities to be processed; The number of common attributes between the entity to be processed and the first entity is counted and used as the first quantity; Calculate the ratio of the first quantity to the number of first entity attributes, and use this as the first ratio. If the similarity value is greater than the first threshold, then the entity to be processed is regarded as the second entity, and the first ratio is regarded as the similarity between the second entity and the first entity; Otherwise, if the traversal of the knowledge graph is not completed, the process jumps to the step of sequentially extracting entities from the knowledge graph as entities to be processed.

3. The enterprise business model recommendation method according to claim 1, characterized in that, The determination of the scarcity index based on the number of entities in each second associated entity set and the total number of business model entities includes: The scarcity index is determined based on the first formula, the number of entities in each second associated entity set, and the total number of entities in all business models. The first formula is: In the formula, For the corresponding number The scarcity index of the third entity connected to a second entity set. As the base, The number of entities in all business models. This represents the number of entities in the second associated entity set.

4. The enterprise business model recommendation method according to claim 1, characterized in that, The determination of the scarcity index based on the number of entities in each second associated entity set and the total number of business model entities includes: For each second set of associated entities, perform the following steps: Calculate the quotient between the number of all business model entities and the number of entities in the second associated entity set, round the quotient to the nearest integer and represent it in binary to obtain the data to be processed; Take the rightmost data from the data to be processed and shift the data to the right. Based on the second formula, the number of right shifts, and the rightmost data retrieved, update the second cumulative sum, where the second formula is: In the formula, This is the updated second cumulative sum. This is the second cumulative sum before the update. To retrieve the rightmost data, This represents the number of right shifts; If the data to be processed has not been traversed completely, then proceed to the step of taking out the rightmost data from the data to be processed and shifting the data to the right. Otherwise, the second summation is used as the scarcity index.

5. The enterprise business model recommendation method according to claim 1, characterized in that, The determination of multiple matching degrees based on the multiple connection frequency sets and the multiple scarcity indices includes: For each of the plurality of third entities, perform the following steps respectively: Extract the set of connection frequencies corresponding to the third entity as the set of connection frequencies to be processed; The matching degree is determined based on the third formula, the set of connection frequencies to be processed, and the multiple scarcity indices, wherein the third formula is: In the formula, For matching degree, For the connection frequencies to be processed, the corresponding number is... The connection frequency of the second entity set For the corresponding number The scarcity index of the third entity connected to a second entity set. This represents the total number of entities in the second entity set.

6. A business model recommendation device for enterprises, characterized in that, For implementing the enterprise business model recommendation method as described in any one of claims 1-5, the enterprise business model recommendation apparatus comprises: The keyword entity acquisition module is used to acquire multiple first entities, where entities are connected to other entities through attributes to form a knowledge graph, and the first entities are keywords used to search for target business models; The keyword expansion module is used to determine, for each first entity, multiple entities similar to the first entity from the knowledge graph based on multiple attributes of the first entity as multiple second entities, and construct the multiple second entities into a second entity set, thereby obtaining multiple second entity sets; The business model entity search module is used to find multiple business model entities that are connected to entities in the multiple second entity sets through business model attributes from multiple business model entities, and to serve as multiple third entities. as well as, The enterprise business model recommendation module is used to select business model entities for recommendation from the plurality of third entities based on the similarity between the second entity and the first entity, the number of attributes of the second entity connected to the third entity, and the proportion of the third entity in all business model entities.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 5 above.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5 above.

Images