Enterprise transformation information generation method and device, storage medium, and electronic device

Abstract

The present disclosure relates to the computer field, and provides a method and device for generating enterprise transformation information, a computer storage medium, and an electronic device. The method includes: obtaining text information, classified data, and network information related to a target enterprise; determining a first transformation score and a first transformation description based on the text information, determining a second transformation score and a second transformation description based on the classified data, and determining a third transformation score and a third transformation description based on the network information; determining an enterprise transformation score according to the first transformation score, the second transformation score, and the third transformation score, and integrating the first transformation description, the second transformation description, and the third transformation description to obtain an enterprise transformation description; generating enterprise transformation information corresponding to the target enterprise according to the enterprise transformation score and the enterprise transformation description. The present disclosure can obtain data analysis from multiple data sources and generate enterprise transformation information, avoiding manual monitoring, thereby reducing costs and improving efficiency.

Description

Background Art

[0002] Enterprise transformation monitoring helps the government support related enterprises. Macro-level enterprise transformation monitoring and analysis can also reflect changes in the business environment and economic trends, providing a basis for policy making. In order to monitor enterprise transformation, existing technologies usually rely on manual analysis of the business scope description reported by the enterprise itself, such as Figure 1 As shown, it can be seen that the company is moving from a single real estate development industry to more industries.

[0003] However, monitoring enterprise transformation through manual analysis has the problems of high cost, low efficiency and non-automation. In addition, the data source is single and only relies on the business scope reported by the enterprise itself. The information may be delayed, resulting in low monitoring efficiency and poor accuracy.

[0004] In view of this, there is an urgent need in this field to develop a new method and device for generating enterprise transformation information.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure. Summary of the invention

[0006] The purpose of the present disclosure is to provide a method for generating enterprise transformation information, an enterprise transformation information generating device, a computer storage medium and an electronic device, thereby improving the efficiency and accuracy of enterprise transformation monitoring at least to a certain extent.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0008] According to a first aspect of the present disclosure, a method for generating enterprise transformation information is provided, characterized by comprising:

[0009] Obtain text information, classified data and network information related to the target enterprise;

[0010] Determine a first transformation score and a first transformation description based on the text information, determine a second transformation score and a second transformation description based on the classification data, and determine a third transformation score and a third transformation description based on the relationship network information;

[0011] Determine an enterprise transformation score according to the first transformation score, the second transformation score, and the third transformation score, and integrate the first transformation description, the second transformation description, and the third transformation description to obtain an enterprise transformation description;

[0012] Enterprise transformation information corresponding to the target enterprise is generated according to the enterprise transformation score and the enterprise transformation description.

[0013] In an exemplary embodiment of the present disclosure, the text information includes historical text information and current text information;

[0014] The determining of the first transformation score and the first transformation description based on the text information includes:

[0015] Calculating a first similarity between the historical text information and the current text information, and determining the first transformation score according to the first similarity;

[0016] The historical text information is compared with the current text information to generate the first transformation description.

[0017] In an exemplary embodiment of the present disclosure, the calculating the first similarity between the historical text information and the current text information includes:

[0018] Performing word segmentation on the historical text information and the current text information respectively;

[0019] Calculate a first TF-IDF vector corresponding to the historical text information based on the word segmentation corresponding to the historical text information;

[0020] Calculate a second TF-IDF vector corresponding to the current text information based on the word segmentation corresponding to the current text information;

[0021] The distance between the first TF-IDF vector and the second TF-IDF vector is calculated to obtain the first similarity.

[0022] In an exemplary embodiment of the present disclosure, determining the first transformation score according to the first similarity includes:

[0023] Obtain a difference between 1 and the first similarity, and use the difference as the first transformation score.

[0024] In an exemplary embodiment of the present disclosure, the classification data includes historical classification data and current classification data;

[0025] Determining a second transformation score and a second transformation description based on the classification data comprises:

[0026] Calculating a second similarity between the historical classification data and the current classification data, and determining the second transformation score according to the second similarity;

[0027] The historical classification data and the current classification data are compared to generate the second transformation description.

[0028] In an exemplary embodiment of the present disclosure, the historical classification data and the current classification data are sparse scattered point data;

[0029] The calculating the second similarity between the historical classification data and the current classification data, and determining the second transformation score according to the second similarity, comprises:

[0030] Comparing the current classification data with the historical classification data;

[0031] When there is classification data different from the historical classification data in the current classification data, the second transformation score is determined to be 1.

[0032] In an exemplary embodiment of the present disclosure, the historical classification data and the current classification data are dense scattered data;

[0033] The calculating the second similarity between the historical classification data and the current classification data, and determining the second transformation score according to the second similarity, comprises:

[0034] Obtaining a third TF-IDF vector based on the historical classification data, and obtaining a fourth TF-IDF vector based on the current classification data;

[0035] calculating a distance between the third TF-IDF vector and the fourth TF-IDF vector to obtain the second similarity;

[0036] Obtain a difference between 1 and the second similarity, and use the difference as the second transformation score.

[0037] In an exemplary embodiment of the present disclosure, the relationship network data includes historical relationship network data and current relationship network data.

[0038] The determining of the third transformation score and the third transformation description based on the relationship network data includes:

[0039] Calculating a third similarity between the historical relationship network data and the current relationship network data, and determining the third transformation score according to the third similarity;

[0040] Acquire a first distance between the target enterprise and other enterprises in the historical relationship network data, and a second distance between the target enterprise and other enterprises in the current relationship network data;

[0041] The first distance and the second distance are compared to generate the third transformation description.

[0042] In an exemplary embodiment of the present disclosure, the calculating the third similarity between the historical relationship network information and the current relationship network information includes:

[0043] Constructing a historical relationship graph based on the historical relationship network information, and constructing a current relationship graph based on the current relationship network information;

[0044] Performing random walks on the historical relationship graph and the current relationship graph respectively to generate a plurality of historical enterprise sequences and a current enterprise sequence;

[0045] Perform feature extraction on the historical enterprise sequence and the current enterprise sequence respectively through a graph neural network to obtain a first vector corresponding to the historical enterprise sequence and a second vector corresponding to the current enterprise sequence;

[0046] The distance between the first vector and the second vector is calculated to obtain the third similarity.

[0047] In an exemplary embodiment of the present disclosure, determining the third transformation score according to the third similarity includes:

[0048] A difference between 1 and the third similarity is obtained, and the difference is used as the third transformation score.

[0049] In an exemplary embodiment of the present disclosure, determining the enterprise transformation score according to the first transformation score, the second transformation score, and the third transformation score includes:

[0050] A weighted sum is performed on the first transformation score, the second transformation score, and the third transformation score to obtain the enterprise transformation score.

[0051] According to a second aspect of the present disclosure, there is provided an enterprise transformation information generating device, characterized in that it comprises:

[0052] Information acquisition module, used to obtain text information, classification data and relationship network information related to the target enterprise;

[0053] an information processing module, configured to determine a first transformation score and a first transformation description based on the text information, determine a second transformation score and a second transformation description based on the classification data, and determine a third transformation score and a third transformation description based on the relationship network information;

[0054] an information integration module, configured to determine an enterprise transformation score according to the first transformation score, the second transformation score, and the third transformation score, and integrate the first transformation description, the second transformation description, and the third transformation description to obtain an enterprise transformation description;

[0055] An information generation module is used to generate enterprise transformation information corresponding to the target enterprise according to the enterprise transformation score and the enterprise transformation description.

[0056] According to a third aspect of the present disclosure, there is provided a computer storage medium on which a computer program is stored, characterized in that when the computer program is executed by a processor, the above-mentioned enterprise transformation information generating method is implemented.

[0057] According to a fourth aspect of the present disclosure, there is provided an electronic device, characterized in that it includes:

[0058] Processor; and

[0059] A memory, configured to store executable instructions of the processor;

[0060] Wherein, the processor is configured to execute the above-mentioned enterprise transformation information generation method by executing the executable instructions.

[0061] It can be seen from the above technical solutions that the enterprise transformation information generation method, enterprise transformation information generation device, computer storage medium and electronic device in the exemplary embodiments of the present disclosure have at least the following advantages and positive effects:

[0062] The enterprise transformation information generation method disclosed in the present invention first obtains text information, classified data and network information related to the target enterprise; then determines the first transformation score and the first transformation description based on the text information, determines the second transformation score and the second transformation description based on the classified data, and determines the third transformation score and the third transformation description based on the network information; then determines the enterprise transformation score according to the first transformation score, the second transformation score and the third transformation score, and integrates the first transformation description, the second transformation description and the third transformation description to obtain the enterprise transformation description; finally, generates the enterprise transformation information corresponding to the target enterprise according to the enterprise transformation score and the enterprise transformation description. Based on the enterprise transformation information, it can be clarified whether the enterprise has transformed, as well as the specific transformation direction. On the one hand, the enterprise transformation information generation method disclosed in the present invention can obtain data analysis from multiple data sources and generate enterprise transformation information, which ensures the timeliness of data acquisition, thereby improving the accuracy of enterprise transformation information; on the other hand, it can avoid manual monitoring and realize the monitoring of enterprise transformation through automation, thereby reducing costs and improving efficiency.

[0063] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0065] Figure 1 A schematic diagram of an interface showing enterprise transformation information in related technologies;

[0066] Figure 2 A schematic diagram showing a process of a method for generating enterprise transformation information in an exemplary embodiment of the present disclosure;

[0067] Figure 3 A schematic diagram showing a process of obtaining a first similarity in an exemplary embodiment of the present disclosure is shown;

[0068] Figure 4 A schematic diagram of an interface showing a first transition score and a first transition description in an exemplary embodiment of the present disclosure;

[0069] Figure 5 A schematic diagram of an interface showing a transformation score and a transformation description determined based on the enterprise's purchased commodity categories in an exemplary embodiment of the present disclosure;

[0070] Figure 6 A schematic diagram of a process for determining a third transition score and a third transition description in an exemplary embodiment of the present disclosure is shown;

[0071] Figure 7 A schematic diagram showing a process of determining a third transition score in an exemplary embodiment of the present disclosure is shown;

[0072] Figure 8 A schematic diagram showing the structure of a directed graph constructed according to historical relationship network information of a target enterprise in an exemplary embodiment of the present disclosure;

[0073] Fig. 9 A schematic diagram showing an interface of a directed graph constructed according to current relationship network information of a target enterprise in an exemplary embodiment of the present disclosure;

[0074] Fig.10 A schematic diagram showing an interface of enterprise transformation information in an exemplary embodiment of the present disclosure;

[0075] Fig.11 A schematic diagram showing the structure of an enterprise transformation information generating device in an exemplary embodiment of the present disclosure;

[0076] Fig.12 A schematic diagram showing the structure of a computer storage medium in an exemplary embodiment of the present disclosure;

[0077] Fig.13 A schematic structural diagram of an electronic device in an exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0078] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0079] The terms "a", "an", "the" and "said" are used in this specification to indicate the presence of one or more elements / components / etc.; the terms "including" and "having" are used to express an open-ended inclusion and mean that additional elements / components / etc. may exist in addition to the listed elements / components / etc.; the terms "first" and "second" etc. are used only as labels and are not intended to limit the quantity of their objects.

[0080] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and their repeated descriptions will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities.

[0081] The exemplary system architecture of the technical solution of the embodiment of the present disclosure may specifically include a terminal device, a network, and a server. The terminal device may be a terminal device with a display unit such as a smart phone, a portable computer, or a tablet computer. The user may send a request to generate enterprise transformation information about the target enterprise to the server through the terminal device; the network is a medium for providing a communication link between the terminal device and the server. The network may include various connection types, such as a wired communication link, a wireless communication link, etc. In the embodiment of the present disclosure, the network between the terminal device and the server may be a wireless communication link, specifically a mobile network, which may send a request to generate enterprise transformation information to the server so that the server obtains text information, classified data, and relationship network information related to the target enterprise, and then obtains enterprise transformation information corresponding to the target enterprise by analyzing the information. The enterprise transformation information may be presented on the display interface of the terminal device for the user to analyze and derive the transformation direction and degree of the target enterprise.

[0082] It should be understood that the number of terminal devices, networks and servers is only illustrative. According to the implementation requirements, there can be any number of terminal devices, networks and servers. It is worth noting that the server in the present disclosure can be an independent server or a server cluster formed by multiple servers.

[0083] It is worth noting that the server can also return the acquired text information, classification data and relationship network information related to the target enterprise to the terminal device through the network, so that the terminal device can analyze the information to obtain the enterprise transformation information corresponding to the target enterprise, and present the enterprise transformation information on the display interface of the terminal device for the user to analyze and derive the transformation direction and degree of the target enterprise.

[0084] In the related technologies disclosed in the present invention, the monitoring of enterprise transformation mainly relies on manual monitoring, where monitoring personnel compare the text descriptions of the business scope and change records of the enterprise in different time periods to determine whether the enterprise has undergone transformation. However, the manual monitoring method has two disadvantages: (1) it cannot be automated and requires manual analysis of each enterprise, which is costly and inefficient; (2) the data source is single and only relies on the business scope reported by the enterprise itself, and the information may be delayed.

[0085] In view of the problems existing in the related technologies, the present disclosure proposes a method for generating enterprise transformation information, which can be executed by a server or by a terminal device. Figure 2 A flow chart showing a method for generating enterprise transformation information is shown, Figure 2 As shown, the enterprise transformation information generation method includes:

[0086] Step S210: Acquire text information, classification data and relationship network information related to the target enterprise;

[0087] Step S220: determining a first transformation score and a first transformation description based on the text information, determining a second transformation score and a second transformation description based on the classification data, and determining a third transformation score and a third transformation description based on the relationship network information;

[0088] Step S230: determining an enterprise transformation score according to the first transformation score, the second transformation score, and the third transformation score, and integrating the first transformation description, the second transformation description, and the third transformation description to obtain an enterprise transformation description;

[0089] Step S240: generating enterprise transformation information corresponding to the target enterprise according to the enterprise transformation score and the enterprise transformation description.

[0090] The enterprise transformation information generation method disclosed in the present invention acquires enterprise transformation information by collecting and analyzing multi-source data. On the one hand, it can acquire data from multiple data sources for analysis and generate enterprise transformation information, thereby ensuring the timeliness of data acquisition and thereby improving the accuracy of enterprise transformation information. On the other hand, it can avoid manual monitoring and achieve enterprise transformation monitoring through automation, thereby reducing costs and improving efficiency.

[0091] The following is a detailed description of each step of the enterprise transformation information generation method.

[0092] In step S210, text information, classification data and relationship network information related to the target enterprise are obtained.

[0093] In an exemplary embodiment of the present disclosure, in order to determine whether the target enterprise has undergone transformation, the user can obtain data related to the target enterprise from servers of multiple platforms through a terminal device, and analyze the obtained multi-source data to obtain the enterprise transformation information of the target enterprise. In an embodiment of the present disclosure, three types of data related to the target enterprise can be obtained, namely text information, classified data and network information, wherein the text information is specifically a text description and change record of the target enterprise's business scope, which can be obtained from the Administration for Industry and Commerce or Tianyancha, Qichacha, and can also crawl the public texts from sources such as the official website of the enterprise and portal websites to obtain text related to the business scope of the enterprise; the classified data is mainly hash data related to the operation of the target enterprise, for example, it can be the category of goods purchased by the enterprise, the category of goods sold by the enterprise, the type of business license held by the enterprise, the type of tax paid by the enterprise, etc., and the above-mentioned types of classified data can be obtained from online and offline sales and procurement channels, various enterprise purchase platforms / e-commerce websites, industrial and commercial bureaus, tax bureaus, etc.; the network information includes the supply and demand and transaction relationship between the target enterprise and other enterprises, and the network information can be obtained from data sources such as transaction data on the enterprise matchmaking platform and related information reported by the enterprise.

[0094] Furthermore, for the business change categories obtained by Tianyancha and Qichacha websites, it is only necessary to record the text information of the business scope before and after the change when the change occurs. For the text information related to the business scope of the enterprise crawled from the official website of the enterprise, the update frequency of the text information can be manually defined, such as crawling the text once a month; for the data such as the type of business license held by the enterprise and the type of tax paid by the enterprise, it is only necessary to record the newly added categories when the change occurs. The update frequency of other data depends on the frequency of the enterprise's behavior. For example, the enterprise makes several purchases on a certain enterprise procurement platform every month, and the update frequency can be defined as monthly; similarly, the acquisition of relationship network information can be defined as monthly based on the frequency of enterprise transactions. It is worth noting that the manually defined update frequency can also be other frequencies, not limited to monthly, and the embodiments of the present disclosure do not make specific limitations on this.

[0095] In step S220, a first transformation score and a first transformation description are determined based on the text information, a second transformation score and a second transformation description are determined based on the classification data, and a third transformation score and a third transformation description are determined based on the relationship network information.

[0096] In the exemplary embodiment of the present disclosure, since it is to determine whether the target enterprise has undergone transformation, it is necessary to compare the current state of the target enterprise with the historical state. Therefore, when collecting text information, classified data and network information, it is necessary to collect corresponding historical information and current information. That is to say, the text information includes historical text information and current text information, the classified data includes historical classified data and current classified data, and the network information includes historical network information and current network information. It is worth noting that the history and current in this application correspond to a time period, not a time point. For example, the historical text information can be the text description and change record of the business scope of the enterprise in the previous month, and the current text information is the text description and change record of the business scope of the enterprise in the current month, and so on.

[0097] When determining the first transformation score and the first transformation description based on text information, the historical text information and the current text information can be vectorized, and the first similarity between the current text information and the historical text information can be calculated based on the vectors corresponding to the two. Then, the first transformation score is determined based on the first similarity, and the historical text information and the current text information are compared to generate a first transformation description.

[0098] Figure 3 A schematic diagram of the process of obtaining the first similarity is shown, such as Figure 3 As shown, in step S301, the historical text information and the current text information are segmented respectively; in step S302, the first TF-IDF vector corresponding to the historical text information is calculated based on the segmented words corresponding to the historical text information; in step S303, the second TF-IDF vector corresponding to the current text information is calculated based on the segmented words corresponding to the current text information; in step S304, the distance between the first TF-IDF vector and the second TF-IDF vector is calculated to obtain a first similarity.

[0099] When the historical text information and the current text information are segmented, the Jieba library in Python can be used to segment the historical text information and the current text information into texts composed of multiple segmented words. After the segmentation is completed, the first TF-IDF vector and the second TF-IDF vector corresponding to the historical text information and the current text information can be calculated according to the TF-IDF algorithm. Taking the calculation of the first TF-IDF vector as an example, the calculation process of the vector is explained:

[0100] Calculate the word frequency TF. The specific expression is shown in formula (1):

[0101]

[0102] Among them, a certain word is a word in the Jieba library, the text is the historical text information, the number of times a certain word appears in the text is the number of times the word appears in the historical text information, and the total number of words in the text is the number of segmented words contained in the historical text information.

[0103] Calculate the inverse document frequency IDF. The specific expression is shown in formula (2):

[0104]

[0105] The total number of texts is the total number of texts included in the Jieba library, and the number of texts containing the word is the number of texts containing the word in the Jieba library.

[0106] After obtaining the TF value and IDF value, multiply the two to get the TF-IDF value corresponding to a word, as shown in formula (3):

[0107] TF-IDF=TF×IDF (3)

[0108] By calculating the TF-IDF value corresponding to each word in the Jieba library according to formulas (1)-(3), the first TF-IDF vector can be determined according to the TF-IDF values ​​of all words. In other words, each element in the first TF-IDF vector corresponds to the TF-IDF value of each word in the Jieba library in the historical text information.

[0109] According to the above method, the first TF-IDF vector corresponding to the historical text information can be obtained, which is recorded as υ1. Similarly, according to the above method, the second TF-IDF vector corresponding to the current text information can be obtained, which is recorded as υ2. In order to determine whether the target enterprise has undergone transformation, that is, to determine whether the current text information has changed relative to the historical text information, it can be determined by judging the first similarity between υ1 and υ2. In the embodiment of the present disclosure, cosine distance, Euclidean distance, Mahalanobis distance, Manhattan distance, etc. can be used for similarity judgment. Taking cosine distance as an example, formula (4) can be used to calculate the first similarity between υ1 and υ2, as follows:

[0110]

[0111] Furthermore, the first transformation score can be determined according to the first similarity. Specifically, the difference between 1 and the first similarity (1-first similarity) can be obtained, and the difference is the first transformation score. From the calculation formula of the first transformation score, it can be seen that the smaller the first similarity, the greater the degree of transformation of the target enterprise; the larger the first similarity, the smaller the degree of transformation of the target enterprise.

[0112] At the same time, by comparing the historical text information with the current text information, the text description of the target enterprise's business scope and the parts that have changed in the change record can be determined, and then the first transformation description can be generated. For example, the text description of the target enterprise's business scope was "real estate development" before the change, and it was "real estate development, building decoration, building decoration material distribution, car rental, shopping malls, catering, entertainment***" after the change. Then, through comparison, it can be found that "building decoration, building decoration material distribution, car rental, shopping malls, catering, entertainment***" in the current text information are all newly added business scopes. Therefore, the newly added business scope can be marked as different from the attribute settings of "real estate development" through different font, color, size and other attribute settings. Figure 4 A schematic diagram of the interface of the first transition score and the first transition description is shown, Figure 4 As shown, there are two pieces of transformation information of enterprises, and each piece of transformation information of an enterprise consists of a text description of the business scope before the change, a text description of the business scope after the change, and a first transformation score. According to the transformation score, it can be clear that the transformation degree of the enterprise corresponding to the first transformation information is greater than the transformation degree of the enterprise corresponding to the second transformation information.

[0113] In an exemplary embodiment of the present disclosure, a second transformation score and a second transformation description can also be determined based on the classification data. Similar to text information, the classification data also includes historical classification data and current classification data, wherein the historical classification data represents the classification data of the previous time period corresponding to the classification data of the current time period. In an embodiment of the present disclosure, the classification data is specifically enterprise operation classification data, for example, including enterprise purchase commodity categories, enterprise sales commodity categories, enterprise business license type, enterprise tax payment type, etc. These classification data can be obtained from online and offline sales and procurement channels, various enterprise purchase platforms / e-commerce websites, industrial and commercial bureaus, tax bureaus and other platforms or institutions. Similar to obtaining the first transformation score and the first transformation description, the second transformation score can be determined by calculating the second similarity between the historical classification data and the current classification data, and the second transformation description can be generated by comparing the historical classification data with the current classification data.

[0114] When determining the second transformation score, different methods can be used for different classified data. Specifically, for data such as the type of business license held by the enterprise and the tax paid by the enterprise, the update frequency is low, and it is only necessary to record the newly added category when the change occurs. Therefore, this type of data can be regarded as sparse hash data. For data such as the categories of goods purchased by the enterprise and the categories of goods sold by the enterprise, the update frequency is high. For example, some enterprises will make multiple purchases on the enterprise procurement platform every month, etc., so this type of data can be regarded as dense hash data. For sparse hash data, by comparing the current classified data with the historical classified data, when it is determined that there is classified data different from the historical classified data in the current classified data, the second transformation score is determined to be 1, otherwise it is 0; for dense hash data, the second transformation score can be determined by calculating the similarity between the current classified data and the historical classified data. Specifically, similarity calculation can also be performed based on the TF-IDF idea.

[0115] Taking enterprise procurement data as an example, we can use a calculation formula similar to formula (1)-(2) to calculate the TF and IDF values ​​corresponding to the classified data, as shown in formula (3)-(4):

[0116]

[0117]

[0118] Among them, the target category products are products of any category in the category library, and the category library is a collection of all product categories obtained based on the statistics of all enterprises' online and offline sales and procurement channels and various enterprise procurement platforms / e-commerce websites' procurement history.

[0119] Next, according to formula (5), the TF-IDF value in the third TF-IDF vector corresponding to the historical classification data and the TF-IDF value in the fourth TF-IDF vector corresponding to the current classification data can be obtained:

[0120] TF-IDF=TF×IDF (5)

[0121] According to the calculation of formulas (3)-(5), the third TF-IDF vector corresponding to the historical classification data and the fourth TF-IDF vector corresponding to the current classification data can be obtained. Each element in the vector corresponds to the TF-IDF score of each commodity category in the category library in the historical time period or the current time period procurement vector of the target enterprise.

[0122] Similar to calculating the first transformation score, the second transformation score can be determined by calculating the second similarity between the third TF-IDF vector and the fourth TF-IDF vector. Taking the cosine distance as an example to calculate the second similarity, the specific calculation formula is shown in formula (6):

[0123]

[0124] Among them, υ3 is the third TF-IDF vector, and υ4 is the fourth TF-IDF vector.

[0125] After obtaining the second similarity, the difference between 1 and the second similarity can be obtained, and the difference can be used as the second transformation score, that is, (1-second similarity). Similarly, the smaller the second similarity, the greater the degree of transformation of the target enterprise. In addition, the second transformation description can be generated by comparing the historical classification data with the current classification data. Figure 5 The following is a schematic diagram of the interface for the transformation score and transformation description determined based on the commodity categories purchased by the enterprise, as shown in Figure 5 As shown in the figure, the historical purchase category of a company is "office desks and chairs", and the current purchase category is "office desks and chairs, blood glucose meter". "Blood glucose meter" is added, so "blood glucose meter" can be marked with a different font, color, and size from "office desks and chairs". Figure 5 From the second set of information, we can see that the historical purchasing categories of a certain enterprise are "office desks and chairs, blood glucose meters", and the current purchasing categories are "office desks and chairs, blood glucose meters, monitors". "Monitors" have been newly added, so "monitors" can be labeled with fonts, colors, and sizes different from those of "office desks and chairs, blood glucose meters". The transformation score corresponding to the first set of information is 0.95, and the transformation score corresponding to the second set of information is 0.1, indicating that the transformation degree of the enterprise corresponding to the first set of information is greater than that of the enterprise corresponding to the second set of information.

[0126] In an exemplary embodiment of the present disclosure, there are multiple types of classified data, so the second transformation score and the second transformation description corresponding to each type of classified data can be obtained. When all transformation scores and transformation descriptions are obtained based on text information, classified data and relationship network information and integrated, the multiple transformation scores are weightedly summed to obtain the enterprise transformation score corresponding to the target enterprise, and the multiple transformation descriptions are superimposed to obtain the enterprise transformation description corresponding to the target enterprise.

[0127] It is worth noting that when updating dense hash data such as enterprise purchase commodity categories and enterprise sales commodity categories, since the frequency of enterprise behavior is not fixed, the update frequency can be defined on a monthly basis. Of course, the update frequency can also be defined on a half-monthly, quarterly, etc. In addition, the number of purchases of the enterprise is used when calculating TF and IDF. However, due to the sparse nature of the enterprise's procurement behavior in various categories, in order to improve the accuracy of the calculation results, the data corresponding to the number of purchases in the historical classification data and the current classification data can be defined as the number of purchases of various categories of goods by the enterprise from the previous month to the previous year and the number of purchases of various categories of goods by the enterprise from the current month to the previous year. For example, if the current month is April 2021, the number of purchases contained in the historical classification data is the number of purchases of various categories of goods by the enterprise from April 1, 2020 to March 31, 2021, and the number of purchases contained in the current classification data is the number of purchases of various categories of goods by the enterprise from May 1, 2020 to April 30, 2021.

[0128] In an exemplary embodiment of the present disclosure, by sorting out the target enterprise's network information, the supply, demand, and transaction relationship between the target enterprise and other enterprises can be clarified. The network information can be obtained from information sources such as transaction data on the enterprise matchmaking platform and related information reported by the enterprise. According to the update frequency of the network information, the current network information and the corresponding historical network information can be obtained. For example, when the network information is updated monthly, the current network information can be the enterprise information that has a supply, demand, and transaction relationship with the target enterprise in the current month, and the historical network information can be the enterprise information that has a supply, demand, and transaction relationship with the target enterprise last month, and so on.

[0129] Likewise, a third transformation score and a third transformation description corresponding to the target enterprise may be determined based on the historical relationship network information and the current relationship network information. Figure 6 A schematic diagram of the process of determining the third transition score and the third transition description is shown, such as Figure 6 As shown, in step S601, the third similarity between the historical network information and the current network information is calculated, and the third transformation score is determined according to the third similarity; in step S602, the first distance between the target enterprise and other enterprises in the historical network information, and the second distance between the target enterprise and other enterprises in the current network information are obtained; in step S603, the first distance and the second distance are compared to generate a third transformation description.

[0130] Step S601 can be based on Figure 7 The flowchart shown is implemented as follows:

[0131] In step S701, a historical relationship graph is constructed based on the historical relationship network information, and a current relationship graph is constructed based on the current relationship network information.

[0132] In order to clearly analyze the changes in the target enterprise's relationship network, the enterprises that have supply, demand and transaction relationships with the target enterprise can be analyzed based on the graph structure. Specifically, the target enterprise and the enterprises that have supply, demand and transaction relationships with them can be used as nodes, and the supply, demand and transaction relationships between the target enterprise and other enterprises can be used as edges to form a directed graph. The direction of the edges in the directed graph represents the supply, demand and transaction relationships between the enterprises. Figure 8 The structure diagram of the directed graph constructed based on the historical relationship network information of the target enterprise is shown in FIG. Figure 8 As shown, the target enterprise is enterprise 1, and the enterprises with supply, demand and transaction relationships are enterprise A-enterprise G, among which enterprise A-enterprise C are customers of enterprise 1, so the edge points from enterprise 1 to enterprise A-enterprise C respectively, and enterprise D-enterprise G are suppliers of enterprise 1, so the edge points from enterprise D-enterprise G to enterprise 1. Accordingly, after obtaining the historical relationship network information and current relationship network information related to the target enterprise, a historical relationship graph can be constructed based on the historical relationship network information, and a current relationship graph can be constructed based on the current relationship network information. Furthermore, the weight of the edge can be determined according to the number of transactions between the two enterprises with which the edge exists. The specific method is not specifically limited in this disclosure, as long as the weight is positively correlated with the number of transactions.

[0133] In step S702, random walks are performed on the historical relationship graph and the current relationship graph respectively to generate a plurality of historical enterprise sequences and a current enterprise sequence.

[0134] In an exemplary embodiment of the present disclosure, in the historical relationship graph and the current relationship graph established in step S701, a starting point can be randomly selected, and hyperparameters such as length and number can be fixed to generate multiple historical enterprise sequences and current enterprise sequences, and the trained graph neural network is used to process the historical enterprise sequences and the current enterprise sequences to obtain vectors corresponding to each enterprise in the historical enterprise sequence and the current enterprise sequence. In the process of randomly walking the historical relationship graph and the current relationship graph to generate the historical enterprise sequence and the current enterprise sequence, the walk can be performed according to the weight of the edge. The greater the weight, the greater the probability of selection during the random walk.

[0135] In step S703, feature extraction is performed on the historical enterprise sequence and the current enterprise sequence respectively through a graph neural network to obtain a first vector corresponding to the historical enterprise sequence and a second vector corresponding to the current enterprise sequence.

[0136] In an exemplary embodiment of the present disclosure, the graph neural network may specifically be a SkipGram neural network, which is a type of word2vec model. By inputting a one-hot vector corresponding to any enterprise name in a historical enterprise sequence or a current enterprise sequence into the SkipGram neural network, the input vector may be acted upon by a weight matrix in a hidden layer to output an embedding vector corresponding to the enterprise name. The weight matrix in the hidden layer is obtained by training the SkipGram neural network. For ease of description, the embedding vector obtained by processing the enterprise names in the historical enterprise sequence through the SkipGram neural network is recorded as a first vector, and the embedding vector obtained by processing the enterprise names in the current enterprise sequence through the SkipGram neural network is recorded as a second vector.

[0137] In step S704, the distance between the first vector and the second vector is calculated to obtain the third similarity.

[0138] In an exemplary embodiment of the present disclosure, after obtaining the first vector and the second vector, the third transformation score can be determined by calculating the third similarity between the first vector and the second vector. Similar to the first similarity and the second similarity, the third similarity can also be calculated by calculating the cosine distance, the Euclidean distance, etc. In the embodiment of the present disclosure, the cosine distance is specifically used to determine the third similarity. Furthermore, the difference between 1 and the third similarity (1-third similarity) can also be obtained, and the difference can be used as the third transformation score. Similarly, the smaller the third similarity, the greater the degree of transformation of the target enterprise.

[0139] In step S602 and step S603, a first distance between the embedding vector corresponding to the target enterprise and the embedding vectors corresponding to other enterprises in the historical network information can be calculated, and a second distance between the embedding vector corresponding to the target enterprise and the embedding vectors corresponding to other enterprises in the current network information can be calculated. By comparing the first distance and the second distance, it can be determined whether the current network information has changed relative to the historical network information. Fig. 9 The following is a schematic diagram showing the interface of a directed graph constructed based on the current relationship network information of the target enterprise. Fig. 9 As shown, compared to Figure 8 The directed graph constructed by the historical relationship network information shown in Fig. 9 A supplier enterprise H is added in the network. By comparing the embedding vector of the target enterprise with the distances between other enterprises in the historical network information and other enterprises in the current network information, the changed associated enterprise information can be determined.

[0140] according to Figure 8 and Fig. 9The directed graph shown can determine the third transformation description corresponding to the target enterprise's network information. The third transformation description can be embodied in the form of a graph, or the graph can be converted into text to identify the associated enterprise information in the current network information that is different from the historical network information through different fonts, colors or sizes.

[0141] In step S230, an enterprise transformation score is determined according to the first transformation score, the second transformation score, and the third transformation score, and the first transformation description, the second transformation description, and the third transformation description are integrated to obtain an enterprise transformation description.

[0142] In an exemplary embodiment of the present disclosure, after obtaining the first transformation score, the second transformation score, and the third transformation score, multi-source data fusion can be performed to obtain an enterprise transformation score corresponding to the target enterprise. Specifically, the fusion can be performed in a weighted summation manner, wherein the weight of each transformation score can be an average weight or a weight set based on experience. Taking the average weight as an example, if there are four transformation scores, then the weight corresponding to each transformation score is 0.25. After obtaining the first transformation description, the second transformation description, and the third transformation description, each transformation description can be directly integrated to form an enterprise transformation description corresponding to the target enterprise.

[0143] In step S240, enterprise transformation information corresponding to the target enterprise is generated according to the enterprise transformation score and the enterprise transformation description.

[0144] In an exemplary embodiment of the present disclosure, after obtaining the enterprise transformation score and the enterprise transformation description, the two can be integrated to form enterprise transformation information corresponding to the target enterprise, helping users to intuitively obtain information such as whether the enterprise has undergone transformation and the degree of transformation.

[0145] Fig.10 The schematic diagram of the interface showing enterprise transformation information is shown as Fig.10As shown in the figure, the enterprise transformation information includes the enterprise transformation description and the enterprise transformation score. The enterprise transformation description includes the historical enterprise business scope text, the current enterprise business scope text, the historical enterprise purchase commodity categories, the current enterprise purchase commodity categories, the historical enterprise sales commodity categories, the current enterprise sales commodity categories, the historical relationship network and the current relationship network. The enterprise transformation score is the score value obtained after weighted summation. As can be seen from the figure, the target enterprise has transformed from the initial real estate development to a comprehensive enterprise integrating real estate development, building decoration, building decoration material distribution, car rental, shopping malls, catering, entertainment, etc., and the commodity categories it purchases and sells, as well as the related enterprises, have changed compared with the commodity categories purchased and sold before the transformation, as well as the related enterprises. From the enterprise transformation description, it can be seen that the target enterprise has a large degree of transformation. Correspondingly, the enterprise transformation score has also reached 0.9, which fully demonstrates that the target enterprise has a large degree of transformation, which can help the government and other institutions to support or supervise the target enterprise, or formulate or modify relevant policies in the industry.

[0146] The present disclosure analyzes the text information, classified data and network information related to the target enterprise to obtain the first transformation score and the first transformation description, the second transformation score and the second transformation description, and the third transformation score and the third transformation description, and then determines the enterprise transformation score according to each transformation score, obtains the enterprise transformation description according to each transformation description, and finally obtains the enterprise transformation information of the target enterprise according to the enterprise transformation score and the enterprise transformation description. On the one hand, the technical solution disclosed in the present disclosure can obtain data analysis and generate enterprise transformation information from multiple data sources. Specifically, text information related to the business scope of the enterprise, classified type data related to the business of the enterprise (such as procurement categories, etc.) and enterprise network information can be used as data sources, ensuring the timeliness of data acquisition, and providing all-round detection of enterprise transformation, thereby improving the accuracy of enterprise transformation information; on the other hand, it can avoid manual monitoring, calculate enterprise transformation scores and enterprise transformation descriptions through AI algorithms such as text similarity, graph embedding, and vector similarity, and realize the monitoring of enterprise transformation in this automated way, thereby reducing costs and improving efficiency.

[0147] The present disclosure also provides a device for generating enterprise transformation information. Fig.11 The structure diagram of the enterprise transformation information generating device is shown as follows: Fig.11 As shown, the enterprise transformation information generating device 1100 may include an information acquisition module 1101, an information processing module 1102, an information integration module 1103 and an information generating module 1104. Among them:

[0148] Information acquisition module 1101, used to acquire text information, classification data and relationship network information related to the target enterprise;

[0149] An information processing module 1102 is used to determine a first transformation score and a first transformation description based on the text information, determine a second transformation score and a second transformation description based on the classification data, and determine a third transformation score and a third transformation description based on the relationship network information;

[0150] An information integration module 1103 is used to determine an enterprise transformation score according to the first transformation score, the second transformation score and the third transformation score, and integrate the first transformation description, the second transformation description and the third transformation description to obtain an enterprise transformation description;

[0151] The information generating module 1104 is configured to generate enterprise transformation information corresponding to the target enterprise according to the enterprise transformation score and the enterprise transformation description.

[0152] In one embodiment of the present disclosure, the text information includes historical text information and current text information; the information processing module 1102 includes: a first transition score calculation unit, used to calculate the first similarity between the historical text information and the current text information, and determine the first transition score according to the first similarity; a first transition description generation unit, used to compare the historical text information and the current text information to generate the first transition description.

[0153] In one embodiment of the present disclosure, the first transformation score calculation unit is configured to: perform word segmentation on the historical text information and the current text information respectively; calculate a first TF-IDF vector corresponding to the historical text information based on the word segmentation corresponding to the historical text information; calculate a second TF-IDF vector corresponding to the current text information based on the word segmentation corresponding to the current text information; calculate the distance between the first TF-IDF vector and the second TF-IDF vector to obtain the first similarity.

[0154] In one embodiment of the present disclosure, the first transition score calculation unit is further configured to: obtain a difference between 1 and the first similarity, and use the difference as the first transition score.

[0155] In one embodiment of the present disclosure, the classification data includes historical classification data and current classification data; the information processing module 1102 includes: a second transformation score calculation unit, used to calculate the second similarity between the historical classification data and the current classification data, and determine the second transformation score according to the second similarity; a second transformation description generation unit, used to compare the historical classification data and the current classification data to generate the second transformation description.

[0156] In one embodiment of the present disclosure, the historical classification data and the current classification data are sparse hash data; the second transformation score calculation unit is configured to: compare the current classification data with the historical classification data; when there is classification data in the current classification data that is different from the historical classification data, determine that the second transformation score is 1.

[0157] In one embodiment of the present disclosure, the historical classification data and the current classification data are dense hash data; the second transformation score calculation unit is configured to: obtain a third TF-IDF vector based on the historical classification data, and obtain a fourth TF-IDF vector based on the current classification data; calculate the distance between the third TF-IDF vector and the fourth TF-IDF vector to obtain the second similarity; obtain the difference between 1 and the second similarity, and use the difference as the second transformation score.

[0158] In one embodiment of the present disclosure, the relationship network data includes historical relationship network information and current relationship network information; the information processing module 1102 includes: a third transformation score calculation unit, used to calculate the third similarity between the historical relationship network information and the current relationship network information, and determine the third transformation score according to the third similarity; a distance calculation unit, used to obtain a first distance between the target enterprise and other enterprises in the historical relationship network information, and a second distance between the target enterprise and other enterprises in the current relationship network information; a third transformation description generation unit, used to compare the first distance and the second distance to generate the third transformation description.

[0159] In one embodiment of the present disclosure, the third transformation score calculation unit is configured to: construct a historical relationship graph based on the historical relationship network information, and construct a current relationship graph based on the current relationship network information; perform random walks on the historical relationship graph and the current relationship graph respectively to generate multiple historical enterprise sequences and current enterprise sequences; perform feature extraction on the historical enterprise sequence and the current enterprise sequence respectively through a graph neural network to obtain a first vector corresponding to the historical enterprise sequence and a second vector corresponding to the current enterprise sequence; calculate the distance between the first vector and the second vector to obtain the third similarity.

[0160] In one embodiment of the present disclosure, the third transition score calculation unit is further configured to: obtain a difference between 1 and the third similarity, and use the difference as the third transition score.

[0161] In one embodiment of the present disclosure, the information integration module 1103 is configured to: perform weighted summation on the first transformation score, the second transformation score, and the third transformation score to obtain the enterprise transformation score.

[0162] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0163] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0164] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0165] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0166] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0167] Refer to the following Fig.12 The electronic device 1200 according to this embodiment of the present invention is described. Fig.12 The electronic device 1200 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0168] like Fig.12 As shown, the electronic device 1200 is in the form of a general computing device. The components of the electronic device 1200 may include, but are not limited to: the at least one processing unit 1210, the at least one storage unit 1220, a bus 1230 connecting different system components (including the storage unit 1220 and the processing unit 1210), and a display unit 1240.

[0169] The storage unit stores program codes, which can be executed by the processing unit 1210, so that the processing unit 1210 performs the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification. For example, the processing unit 1210 can perform the following steps: Figure 2 Step S210 shown in: obtaining text information, classification data and network information related to the target enterprise; step S220: determining a first transformation score and a first transformation description based on the text information, determining a second transformation score and a second transformation description based on the classification data, and determining a third transformation score and a third transformation description based on the network information; step S230: determining an enterprise transformation score according to the first transformation score, the second transformation score and the third transformation score, and integrating the first transformation description, the second transformation description and the third transformation description to obtain an enterprise transformation description; in step S240, generating enterprise transformation information corresponding to the target enterprise according to the enterprise transformation score and the enterprise transformation description.

[0170] The storage unit 1220 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 12201 and / or a cache storage unit 12202 , and may further include a read-only storage unit (ROM) 12203 .

[0171] The storage unit 1220 may also include a program / utility 12204 having a set (at least one) of program modules 12205, such program modules 12205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0172] Bus 1230 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0173] The electronic device 1200 may also communicate with one or more external devices 1400 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1200, and / or communicate with any device that enables the electronic device 1200 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 1250. Furthermore, the electronic device 1200 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 1260. As shown, the network adapter 1260 communicates with other modules of the electronic device 1200 via a bus 1230. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0174] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0175] In an exemplary embodiment of the present disclosure, a computer storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to perform the steps of various exemplary implementations of the present invention described in the above "Exemplary Method" section of the present specification.

[0176] refer to Fig.13 As shown, a program product 1300 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0177] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0178] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0179] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0180] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0181] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0182] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A method for generating enterprise transformation information, characterized in that, it includes: Obtain text information, classification data, and relationship network information related to the target enterprise; wherein, the text information includes the business scope text description and change information of the target enterprise, the classification data includes hash data related to the operation of the target enterprise, and the relationship network information includes the supply-demand relationship and transaction relationship between the target enterprise and other enterprises; Determine the first transformation score and the first transformation description based on the text information, determine the second transformation score and the second transformation description based on the classification data, and determine the third transformation score and the third transformation description based on the relationship network information; Determine the enterprise transformation score according to the first transformation score, the second transformation score, and the third transformation score, and integrate the first transformation description, the second transformation description, and the third transformation description to obtain the enterprise transformation description; Generate enterprise transformation information corresponding to the target enterprise according to the enterprise transformation score and the enterprise transformation description.

2. The method according to claim 1, characterized in that, the text information includes historical text information and current text information; The determining the first transformation score and the first transformation description based on the text information includes: Calculate the first similarity between the historical text information and the current text information, and determine the first transformation score according to the first similarity; Compare the historical text information and the current text information to generate the first transformation description.

3. The method according to claim 2, characterized in that, The calculating the first similarity between the historical text information and the current text information includes: Segment the historical text information and the current text information respectively; Calculate the first TF-IDF vector corresponding to the historical text information based on the words segmented from the historical text information; Calculate the second TF-IDF vector corresponding to the current text information based on the words segmented from the current text information; Calculate the distance between the first TF-IDF vector and the second TF-IDF vector to obtain the first similarity.

4. The method according to claim 3, characterized in that, The determining the first transformation score according to the first similarity includes: Obtain the difference between 1 and the first similarity, and use the difference as the first transformation score.

5. The method according to claim 1, characterized in that, the classification data includes historical classification data and current classification data; The determining the second transformation score and the second transformation description based on the classification data includes: Calculate the second similarity between the historical classification data and the current classification data, and determine the second transformation score according to the second similarity; Compare the historical classification data and the current classification data to generate the second transformation description.

6. The method according to claim 5, characterized in that, the historical classification data and the current classification data are sparse hash data; The calculating the second similarity between the historical classification data and the current classification data, and determining the second transformation score according to the second similarity, comprises: Comparing the current classification data with the historical classification data; When there is classification data different from the historical classification data in the current classification data, the second transformation score is determined to be 1.

7. The method according to claim 5, It is characterized in that The historical classification data and the current classification data are dense hash data; The calculating the second similarity between the historical classification data and the current classification data, and determining the second transformation score according to the second similarity, comprises: Obtaining a third TF-IDF vector based on the historical classification data, and obtaining a fourth TF-IDF vector based on the current classification data; calculating a distance between the third TF-IDF vector and the fourth TF-IDF vector to obtain the second similarity; Obtain a difference between 1 and the second similarity, and use the difference as the second transformation score.

8. The method according to claim 1, It is characterized in that The relationship network data includes historical relationship network information and current relationship network information; The determining of the third transformation score and the third transformation description based on the relationship network information includes: Calculating a third similarity between the historical relationship network information and the current relationship network information, and determining the third transformation score according to the third similarity; Acquire a first distance between the target enterprise and other enterprises in the historical relationship network information, and a second distance between the target enterprise and other enterprises in the current relationship network information; The first distance and the second distance are compared to generate the third transformation description.

9. The method according to claim 8, It is characterized in that The calculating the third similarity between the historical relationship network information and the current relationship network information includes: Constructing a historical relationship graph based on the historical relationship network information, and constructing a current relationship graph based on the current relationship network information; Performing random walks on the historical relationship graph and the current relationship graph respectively to generate a plurality of historical enterprise sequences and a current enterprise sequence; Perform feature extraction on the historical enterprise sequence and the current enterprise sequence respectively through a graph neural network to obtain a first vector corresponding to the historical enterprise sequence and a second vector corresponding to the current enterprise sequence; The distance between the first vector and the second vector is calculated to obtain the third similarity.

10. The method according to claim 9, It is characterized in that Determining the third transformation score according to the third similarity includes: A difference between 1 and the third similarity is obtained, and the difference is used as the third transformation score.

11. The method according to claim 1, It is characterized in that Determining the enterprise transformation score according to the first transformation score, the second transformation score, and the third transformation score includes: A weighted sum is performed on the first transformation score, the second transformation score, and the third transformation score to obtain the enterprise transformation score.

12. An enterprise transformation information generating device, It is characterized in that include: An information acquisition module, used to acquire text information, classified data and relationship network information related to the target enterprise; wherein the text information includes a text description of the target enterprise's business scope and change information, the classified data includes hash data related to the target enterprise's business, and the relationship network information includes the supply and demand relationship and transaction relationship between the target enterprise and other enterprises; an information processing module, configured to determine a first transformation score and a first transformation description based on the text information, determine a second transformation score and a second transformation description based on the classification data, and determine a third transformation score and a third transformation description based on the relationship network information; an information integration module, configured to determine an enterprise transformation score according to the first transformation score, the second transformation score, and the third transformation score, and integrate the first transformation description, the second transformation description, and the third transformation description to obtain an enterprise transformation description; An information generation module is used to generate enterprise transformation information corresponding to the target enterprise according to the enterprise transformation score and the enterprise transformation description.

13. A computer storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the enterprise transformation information generating method according to any one of claims 1 to 11 is implemented.

14. An electronic device, It is characterized in that include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to execute the enterprise transformation information generating method according to any one of claims 1 to 11 by executing the executable instructions.

Images