CN114510555A

CN114510555A - Method and device for making business strategy and related equipment

Info

Publication number: CN114510555A
Application number: CN202210176656.3A
Authority: CN
Inventors: 于原原
Original assignee: Ping An Puhui Enterprise Management Co Ltd
Current assignee: Ping An Puhui Enterprise Management Co Ltd
Priority date: 2022-02-24
Filing date: 2022-02-24
Publication date: 2022-05-17

Abstract

The invention discloses a method for making a business strategy, which is used for making the business strategy to improve the purchase rate of products. The method provided by the invention comprises the following steps: acquiring a service discussion text and historical user information data of a user in a service system; extracting a content entity and an emotional word corresponding to the content entity from the service discussion text; extracting product attribute characteristics corresponding to the content entities from the service discussion texts, and classifying users in the service system according to the content entities, the product attribute characteristics and the historical user information data; performing emotion analysis on the users in the business system according to the content entities, the product attribute characteristics, the emotion words and the classification results; and formulating a service strategy for the user in the service system according to the emotion analysis result and the historical user information data.

Description

Method and device for making business strategy and related equipment

Technical Field

The present invention relates to the field of artificial intelligence technology, and in particular, to a method and an apparatus for formulating a business strategy, a computer device, and a storage medium.

Background

In the current environment that product sales competition is increasingly intense, users need to be accurately analyzed and appropriate business strategies are formulated to improve the purchase rate of target products, and the traditional mode is that single user comment data and user basic information are used to conduct one-sided analysis to obtain the emotion of the users, so that the calculation of the real emotion values of the users is not accurate enough and the efficiency is low.

Disclosure of Invention

The embodiment of the invention provides a method and a device for formulating a business strategy, computer equipment and a storage medium, which are used for solving the problems that the real emotion value of a user is not accurately calculated and the efficiency is low by the business strategy formulated by a traditional method.

A method for making a business strategy comprises the following steps:

acquiring a service discussion text and historical user information data of a user in a service system;

extracting a content entity and an emotional word corresponding to the content entity from the service discussion text;

extracting product attribute characteristics corresponding to the content entities from the service discussion text, and classifying users in the service system according to the content entities, the product attribute characteristics and the historical user information data;

performing emotion analysis on the users in the business system according to the content entities, the product attribute characteristics, the emotion words and the classification results;

and formulating a service strategy for the user in the service system according to the emotion analysis result and the historical user information data.

An apparatus for making a business strategy, comprising:

the data acquisition module is used for acquiring the service discussion text and the historical user information data of the user in the service system;

the content extraction module is used for extracting a content entity and an emotional word corresponding to the content entity from the service discussion text;

the user classification module is used for extracting the product attribute characteristics corresponding to the content entities from the service discussion text and classifying users in the service system according to the content entities, the product attribute characteristics and the historical user information data;

the emotion analysis module is used for carrying out emotion analysis on the users in the business system according to the content entities, the product attribute characteristics, the emotion words and the classification results;

and the service strategy module is used for making a service strategy for the users in the service system according to the emotion analysis result and the historical user information data.

A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the business policy making method when executing the computer program.

A computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the steps of the above-described business policy making method.

According to the business strategy making method, the business strategy making device, the computer equipment and the storage medium, the business discussion text and the historical user information data of the user are obtained, the content entity and the emotion word corresponding to the content entity are extracted from the business discussion text, the product attribute feature corresponding to the content entity is extracted from the business discussion text, the user is classified, meanwhile, emotion analysis is carried out on the user, the business strategy is made for the corresponding user according to the emotion analysis result and the historical user information data, and the emotion value of the user on the target product is more accurately and efficiently analyzed because the emotion of the user on the target product is more comprehensively analyzed.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.

FIG. 1 is a schematic diagram of an application environment of a method for creating a business strategy according to an embodiment of the present invention;

FIG. 2 is a flow chart of a method for establishing a business strategy according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of a business policy making apparatus according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of a computer device according to an embodiment of the invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The business strategy making method provided by the application can be applied to an application environment shown in fig. 1, wherein the server 101 can be an independent server, or a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, Network service, cloud communication, middleware service, domain name service, security service, Content Delivery Network (CDN), big data, an artificial intelligence platform and the like. In the traditional business strategy making process, the corresponding business strategy is made based on historical data such as basic information data, user business browsing data, user business evaluation data and the like of a user, but the historical data can only partially reflect emotion data of the user, namely, the historical data is used for making pictures of the user, the result is incomplete, even possibly deviates from the emotion direction of the user, the incomplete or even deviating from the emotion direction user picture data cannot play a positive role in making the business strategy, and even can play a negative role, so that a large amount of manpower and material resources are consumed. Therefore, the method collects the discussion data of the user about the service, the discussion data is not limited to the discussion data published by the user on the software, the application or the system of the platform where the service is located, the discussion data also comprises the discussion data which is published on the software, the application or the system of other platforms which are irrelevant to the service and is relevant to the service, the obtained discussion data of the user about the service is analyzed by using a natural language processing technology, the discussion data is combined with historical data, the portrait result of the user is updated, the emotion of the user on the service is comprehensively analyzed to obtain various emotion numerical values of the user on the service, and a service strategy is formulated based on the new portrait result and the emotion numerical values of the user on the service. Because the emotion value is based on the discussion data of the user to the service, the discussion data contains emotion information of more users to the service; the new business strategy making method adds the process of emotion analysis to the user, so the new business strategy is more effective in the execution process.

In this embodiment, the users all refer to the users in the service system if there is no special description.

In an embodiment, as shown in fig. 2, a method for making a business policy is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps S201 to S205.

S201, obtaining a service discussion text and historical user information data of a user in a service system. When the user is exposed to the service for the first time, user-associated service data related to the service is generated, and the content of the user-associated service data includes but is not limited to: the data processing method comprises the following steps of user basic information data, user platform browsing data, user evaluation data, user transacted business data, user feedback data and the like, wherein the form of the user associated business data comprises but is not limited to: the server 101 further operates corresponding text analysis service, digital analysis service, picture analysis service, audio analysis service and video analysis service, and the foregoing various analysis services are used for analyzing corresponding text, digital, picture, audio and video to obtain the user-associated service data. The server 101 stores the user-associated service data as first historical user information data, where the first historical user information data is obtained based on a first platform where the service is located, that is, data associated with a user may be obtained from at least one software, application, or system of the first platform; meanwhile, a second historical user information acquisition application is deployed on the server 101, the information acquisition application acquires user third-party data related to a user from other non-first platforms through a public channel or a public method or an agreement achieving mode (the first platform is a first party, the user is a second party, and the other non-first platforms are third parties), and selects data related to a service from the user third-party data as second historical user information data, and finally the first historical user information data and the second historical user information data jointly form the historical user information data. The service discussion text of the user is sourced from the first platform and the third-party data. Wherein, text data generated by the discussion of the service in at least one software, application or system in the first platform by the user is used as the service discussion text source of the user; the method can also be used for collecting the comment text data from the third-party data, and extracting the comment text data which has a relationship with the business from the comment text data to be used as the business discussion text of the user.

Further, after obtaining the service discussion text data of the user, the service irrelevant information text in the service discussion text is removed by using a preset basic word bank, an industry word bank and a preset text recognition rule to obtain a second service discussion text, where the irrelevant information text includes but is not limited to: the method comprises the steps of sending texts which cannot be identified, texts containing bad information, texts containing advertisement information and false information, and sending basic information of users who issue texts containing the bad information, the texts containing the advertisement information and the false information to a user management system of a platform for processing. And then, modifying the font format of the second service discussion text into a preset target font format to obtain a third service discussion text, so as to avoid the situation that the third service discussion text cannot be identified due to the fact that the font formats of the texts are not uniform in the subsequent steps. And finally, modifying the wrong characters and the different characters in the third service discussion text according to a preset wrong character library and a different character library to obtain a standard service discussion text. The standard business discussion text is a clean text after basic data cleaning, and is basic data for analyzing user emotion by using a natural language processing method subsequently.

S202, extracting a content entity and an emotion word corresponding to the content entity from the service discussion text.

The content entity is a proprietary entity with a specific meaning in the industry, and the content entity has a certain association relationship with the service in the service policy in the embodiment, if the content entity does not have an association relationship with the service, the analysis of the emotion value of the user on the content entity becomes meaningless, and the service policy made according to the meaningless emotion value also has no value.

The emotion words are not only extracted from the service discussion text, but also can be analyzed according to the context of the content entities in the service discussion text, and at least one emotion word is matched from a preset emotion word library to serve as the emotion expression of the user on the content entities. The method is based on the traditional natural language processing technology and machine learning technology, namely, a preset emotion word matching case is learned by a machine, then the machine analyzes new text data to match emotion words, and finally, a matching result of the machine can be corrected in a supervised learning mode to achieve the purpose of supervision and help to improve the accuracy of matching emotion words by the machine.

S203, extracting the product attribute characteristics corresponding to the content entities from the service discussion text, and classifying the users in the service system according to the content entities, the product attribute characteristics and the historical user information data.

Specifically, before corresponding text processing, a decision tree classification model generated in advance based on a Bayesian principle is obtained, wherein the decision tree classification model not only comprises all user types, but also comprises a rule for judging the user types by the users; the user type division can be performed according to the service type discussed by the user, and can be further performed according to the information related to other users such as income, age, gender and the like on the basis of the divided service types, the more detailed user classification can enable the service strategy formulated by the embodiment to have a better beneficial effect, but the granularity of the user classification is further refined to occupy more computer resources on the server 101, so the granularity of the user classification also needs to be balanced according to the residual situation of the computer resources on the server 101, and the method for reasonably distributing the computer resources to achieve the optimal running state of the deployed applications on the server is based on the traditional technology.

Further, before the decision tree classification model is used for analysis, the service discussion text needs to be correspondingly preprocessed to obtain text data to be analyzed. The preprocessing refers to performing operations on the service text data, including but not limited to: stem extraction, morphology reduction, text normalization, noise elimination and text enhancement. The result of preprocessing the service discussion text can improve the efficiency of classifying the users, can quickly process a large amount of user discussion text data, and improves the efficiency of making service strategies. And then processing the text data to be analyzed by using a regular expression to obtain product attribute feature words to be confirmed, and adding the product attribute feature words to be confirmed to a preset feature word to-be-confirmed set. And traversing the feature word to-be-confirmed set, respectively judging whether the feature words of the product attributes to be confirmed exist in a preset feature word library, and if so, adding the corresponding feature words of the product attributes to be confirmed into the product attribute feature set. The product attribute feature words may be physical product attribute feature words (such as clothes, shoes, etc.), or non-physical product attribute feature words (such as insurance products, loan products, etc.). And finally, inputting the content entity, the product attribute feature set and the historical user information data corresponding to the service discussion text into the decision tree classification model to obtain a user classification result. The product attribute feature words are extracted from the text data to be analyzed and are used as one of bases for user classification, so that a strong association relation can be better established between a user and a product, the emotion of the user to the product can be more accurately identified by the business strategy, and the purchase rate of the product related to the business is improved.

S204, according to the content entity, the product attribute characteristics, the emotion words and the classification result, emotion analysis is carried out on the users in the business system.

Specifically, the content entities associated with the users in the target category and the emotion words contained in the associated content entities are firstly obtained from the results of the user classification, and it needs to be specifically stated that the emotion words comprise positive emotions, negative emotions and neutral emotions. The sentiment value of the target category user to the associated content entity is then predicted according to the sentiment words, and conventional methods for calculating the sentiment value include, but are not limited to: naive Bayes, maximum entropy, support vector machine and various neural networks. In this embodiment, since the service discussion text of the user is kept in an irregularly increased state, the naive bayes method is suitable for incrementally calculating the emotion value, and it should be particularly noted that at least two conventional methods can be selected to calculate the emotion value, and then data processing methods such as mean processing and the like are performed according to the calculation results of the at least two conventional methods to obtain the final emotion value. And then, matching at least one target product according to the product attribute characteristics corresponding to the associated content entities, wherein the target product has at least one product attribute characteristic, and if the at least one target product cannot be matched, sending the product attribute characteristics which are not matched to the product to product development related personnel, so that the related personnel can develop a new product according to the product attribute characteristics. After the process of matching at least one target product, establishing an association relationship among the target type users, the target products and the emotion values, and adding the association relationship to a user emotion analysis set, where the association relationship is a one-to-one association relationship, that is, a type of target user corresponds to one target product and then corresponds to one emotion value, and a plurality of one-to-one association relationships are established when a type of target user corresponds to a plurality of target products, for example, a type of target user corresponds to another target product and then corresponds to another emotion value, and the case of emotion values is similar to this and is not repeated. And finally, circulating the step from the step of acquiring the content entities associated with the target category users and the emotion words contained in the associated content entities from the user classification results to the step of adding the association relationship to a user emotion analysis set until all classified users are analyzed.

Further, after the step of analyzing the emotion of the user according to the content entity, the product attribute feature, the emotion word and the result of the user classification, the method further includes: sending the corresponding association relation of the emotion value exceeding a preset emotion value range to a manual auditing system for auditing, updating or deleting the corresponding association relation according to an auditing result, wherein the emotion value exceeding the preset emotion value range indicates that the emotion value data loses use value, if the emotion value exceeds the preset emotion value range and is used again, subsequent calculation is deviated, manual intervention is needed at the moment, and relevant professionals correct, update or directly delete the emotion value after auditing the discussion text data of the user relevant to the emotion value; finally, the step of obtaining the service discussion text of the user to perform emotion analysis on the user is also needed to be performed according to a preset timing task, the change of the association relationship is monitored, because the emotion of the user is in an uncontrollable random change state after the first calculation process is finished, the change of the association relationship needs to be monitored at a constant time, the service strategy is adjusted after the emotion of the user is changed, the monitored time granularity can be reasonably distributed according to the remaining situation of computer resources in the server 101, for example, the frequency of the monitoring process can be properly increased under the situation that the computer resources in the server 101 are abundant, and the frequency of the monitoring process can be properly reduced under the situation that the computer resources in the server 101 are in short supply.

S205, making a business strategy for the users in the business system according to the emotion analysis result and the historical user information data.

Specifically, firstly, according to the association relationship, allocating a preset number of target products to a user in an order from large to small of the emotion value, wherein it is specifically noted that the emotion value refers to positive emotion of the user on the target products and is not negative emotion or neutral emotion, because only the user with positive emotion has a greater probability of purchasing the target products, and meanwhile, the greater the emotion value is, the greater the probability of purchasing the target products is indicated by the user, and the business strategy formulated based on the positive emotion value sorting result can improve the purchase rate of the target products; after distributing a preset number of target products for a user, setting at least one pushing time interval for the target products, setting at least one pushing channel, establishing a pushing relation among the target category users, the target products, the target pushing time interval and the pushing channel, and pushing the target products to the corresponding target users through the set pushing channel when the pushing time interval is met at the current moment.

The pushing time interval may be a certain time interval set by a 24-hour system, or may be a certain time interval in a certain day of a certain month in a certain year, for example, performing daily regular pushing on the target product, and performing activity pushing on the target product. The pushing time interval is further optimized according to the feedback result of the pushing channel, wherein the feedback result of the pushing channel includes but is not limited to: the arrival rate of the push information of the target product (the arrival rate of the push information of the target product at the device of the user may be different in some areas in a certain time interval due to network failure and other factors, which may result in no arrival), and the opening rate of the push information of the target product (although the push information of the target product reaches the device of the user, the user may not click to open and view the push information, because the willingness of the user to open the push information in a certain time interval is low). Further, different pushing times may be set according to other different user information of the target classification user, for example, if the time zones of the target classification users are different, different pushing times need to be set according to the time zone in which the target classification user is located, and different pushing times are set according to the ages of the target classification users.

The push channel also needs to be optimized according to the actual product information push effect, because in the product purchase process, when a user can record that the product is purchased, the user acquires the channel source of the product information, namely, the push channel for the user to generate purchase behavior is recorded, and in the subsequent push channel optimization process, the push channel for the user to generate purchase behavior is enlarged. The push channel comprises at least one push channel of software, application or system of the first platform and a third-party platform which is not the first platform and has a push function (the first platform is a first party, the user is a second party, and the other non-first platforms are third parties).

The push relationship is a one-to-one correspondence relationship, namely, one type of target user corresponds to one target product, then corresponds to one push time interval, and finally corresponds to one push channel, for example, users with high positive emotion values for insurance products push insurance product messages through financial consumption mobile applications such as Paibao, Jingdong finance and the like in six pm to eight pm every day. The application scenario that a plurality of target products are allocated to one type of target users needs to establish a plurality of one-to-one corresponding relations, for example, users who have positive emotion to loan products and insurance products need to establish two one-to-one corresponding relations, one corresponding relation is related to the loan products, and the other corresponding relation is related to the insurance products. The method for establishing the one-to-one correspondence according to the pushing time interval and the pushing channel is similar to the method for establishing the one-to-one correspondence according to the target product, and details are not repeated here.

Further, after the business strategy is formulated for the first time, the business strategy operates in the environment of the server 101, and optimization and adjustment are continuously performed according to the operation effect of the business strategy, wherein the emotion value of the target product is continuously updated by the user, the pushing time interval of the target product is continuously optimized, and the pushing channel of the target product is continuously optimized.

It should be particularly noted that, in this embodiment, for a target product with a neutral emotion, a small number of times of pushing the target product may be performed for the user, and the number of times of pushing may be increased or decreased according to behavior data of the target product and discussion text data of the user.

In the embodiment, by collecting the service discussion text of the user, analyzing the service discussion text and the historical user information data, processing the service discussion text by using a natural language processing technology, classifying users by using a decision classification tree model, extracting product attribute words from the service discussion text to be matched with appropriate target products, extracting emotion words from the service discussion text, predicting emotion values of each type of users for different target products, establishing corresponding emotion association relation according to the emotion value of the user to the target product, establishing a service strategy based on the emotion association relation, and selecting a proper pushing time interval and a proper pushing channel, pushing the product information of the target product to a user, recording subsequent behavior data of the user on the target product, and continuously optimizing the business strategy according to the behavior data.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

In an embodiment, a device for formulating a service policy is provided, and the device for formulating a service policy corresponds to the method for formulating a service policy in the above embodiment one to one. As shown in fig. 3, the business strategy making device includes a data obtaining module 301, a content extracting module 302, a user classifying module 303, an emotion analyzing module 304 and a business strategy module 305. The functional modules are explained in detail as follows:

Further, the data acquisition module further comprises:

the text cleaning submodule is used for removing the service irrelevant information text in the service discussion text by using a preset word stock and an identification rule to obtain a second service discussion text;

the text format processing submodule is used for modifying the font format of the second service discussion text into a preset target font format to obtain a third service discussion text;

and the text wrongly-written character sub-module is used for modifying wrongly-written characters and different characters in the third service discussion text according to a preset wrongly-written character library and a different character library to obtain a standard service discussion text.

Further, the user classification module further comprises:

the classification model submodule is used for acquiring a decision tree classification model generated in advance based on the Bayesian principle;

the text extraction submodule is used for preprocessing the service discussion text to obtain text data to be analyzed;

the regular analysis submodule is used for processing the text data to be analyzed by using a regular expression to obtain product attribute feature words to be confirmed and adding the product attribute feature words to be confirmed to a set to be confirmed;

the traversal judgment sub-module is used for traversing the set to be confirmed and respectively judging whether the product attribute feature words to be confirmed exist in a preset feature word bank or not, and if yes, adding the corresponding product attribute feature words to be confirmed into the product attribute feature set;

and the classified user sub-module is used for inputting the content entity, the product attribute feature set and the historical user information data corresponding to the service discussion text into the decision tree classification model to obtain a user classification result.

Further, the emotion analysis module comprises:

the target information acquisition submodule is used for acquiring the content entity associated with the target category user and the emotion words contained in the associated content entity from the user classification result;

the emotion value prediction sub-module is used for predicting the emotion value of the target category user on the associated content entity according to the emotion words;

the product matching sub-module is used for matching at least one target product according to the product attribute characteristics corresponding to the associated content entities;

the emotion analysis set submodule is used for establishing the association relationship among the target category users, the target products and the emotion values and adding the association relationship to a user emotion analysis set;

and the cyclic analysis submodule is used for cyclically acquiring the content entity associated with the target category user and the emotion words contained in the associated content entity from the user classification result to the step of adding the association relationship to the user emotion analysis set until all the classified user classifications are analyzed.

Further, the emotion analysis module further comprises:

the emotion abnormity auditing submodule is used for sending the corresponding association relation of the emotion value exceeding the preset emotion value range to a manual auditing system for auditing, and updating or deleting the corresponding association relation according to the auditing result;

and the incidence relation monitoring submodule is used for cycling the step of acquiring the service discussion text of the user to the step of carrying out emotion analysis on the user according to a preset timing task and monitoring the change of the incidence relation.

Further, the service policy module further includes:

the target product allocation submodule is used for allocating a preset number of target products for the user according to the sequence of the emotion values from large to small according to the association relation;

a push time interval submodule for setting at least one push time interval;

the pushing channel setting submodule is used for setting at least one pushing channel;

the pushing relation establishing submodule is used for establishing the pushing relation among the target category user, the target product, the optimal pushing time interval and the pushing channel;

and the pushing task execution submodule is used for pushing the target product to the corresponding target category user through the pushing channel when the pushing time interval is met at the current moment.

Wherein the meaning of "first" and "second" in the above modules/units is only to distinguish different modules/units, and is not used to define which module/unit has higher priority or other defining meaning. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to such process, method, article, or apparatus, and such that a division of modules presented in this application is merely a logical division and may be implemented in a practical application in a further manner.

For specific definition of the business policy making device, reference may be made to the above definition of the business policy making method, which is not described herein again. All or part of each module in the business strategy making device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing data involved in the business strategy making method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a business strategy formulation method.

The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like which is the control center for the computer device and which connects the various parts of the overall computer device using various interfaces and lines.

The memory may be used to store the computer programs and/or modules, and the processor may implement various functions of the computer device by running or executing the computer programs and/or modules stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, video data, etc.) created according to the use of the cellular phone, etc.

The memory may be integrated in the processor or may be provided separately from the processor.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the business policy making method in the above embodiments, such as the steps 201 to 205 shown in fig. 2 and extensions of other extensions of the method and related steps. Alternatively, the computer program, when executed by the processor, implements the functions of the modules/units of the business policy making apparatus in the above embodiments, such as the functions of the modules 301 to 305 shown in fig. 3. To avoid repetition, further description is omitted here.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein.

Claims

1. A method for making a business strategy is characterized by comprising the following steps:

2. The method for formulating the business strategy according to claim 1, wherein the step of obtaining the business discussion text of the user further comprises:

removing the service irrelevant information text in the service discussion text by using a preset word bank and an identification rule to obtain a second service discussion text;

modifying the font format of the second service discussion text into a preset target font format to obtain a third service discussion text;

modifying the wrong characters and the different characters in the third service discussion text according to a preset wrong character library and a different character library to obtain a standard service discussion text;

the extracting of the content entity from the service discussion text and the emotion word corresponding to the content entity are specifically as follows:

and extracting a content entity and an emotional word corresponding to the content entity from the standard service discussion text.

3. The method for formulating the business strategy according to claim 1, wherein the step of extracting the product attribute feature corresponding to the content entity from the business discussion text and classifying the user according to the content entity, the product attribute feature and the historical user information data specifically comprises:

obtaining a decision tree classification model generated in advance based on a Bayesian principle;

preprocessing the service discussion text to obtain text data to be analyzed;

processing the text data to be analyzed by using a regular expression to obtain product attribute feature words to be confirmed, and adding the product attribute feature words to be confirmed into a set to be confirmed;

traversing the set to be confirmed, respectively judging whether the product attribute feature words to be confirmed exist in a preset feature word library, and if so, adding the corresponding product attribute feature words to be confirmed into the product attribute feature set;

and inputting the content entity, the product attribute feature set and the historical user information data corresponding to the service discussion text into the decision tree classification model to obtain a user classification result.

4. The method for formulating the business strategy according to claim 1, wherein the step of analyzing the emotion of the user according to the content entity, the product attribute feature, the emotion word and the result of the user classification specifically comprises:

acquiring content entities associated with target category users and emotion words contained in the associated content entities from the user classification result;

predicting the emotion value of the target category user to the associated content entity according to the emotion words;

matching at least one target product according to the product attribute characteristics corresponding to the associated content entities;

establishing an association relation among the target category users, the target products and the emotion values, and adding the association relation to a user emotion analysis set;

and circulating the step of acquiring the content entities associated with the target category users and the emotion words contained in the associated content entities from the user classification result to the step of adding the association relationship to the user emotion analysis set until all the classified users are analyzed.

5. The method for making a business strategy according to claim 4, wherein the step of analyzing emotion of the user according to the content entity, the product attribute feature, the emotion word and the result of the user classification further comprises:

sending the corresponding association relation of the emotion value exceeding the preset emotion value range to a manual auditing system for auditing, and updating or deleting the corresponding association relation according to the auditing result;

and circulating the step from the acquisition of the service discussion text of the user to the step of emotion analysis of the user according to a preset timing task, and monitoring the change of the association relation.

6. The method according to claim 4, wherein the step of formulating the service policy for the corresponding user according to the emotion analysis result and the historical user information data specifically comprises:

distributing a preset number of target products for the user according to the sequence of the emotion values from large to small according to the association relation;

setting at least one pushing time interval;

setting at least one pushing channel;

establishing a pushing relation among the target category user, the target product, the pushing time interval and the pushing channel;

and when the current moment meets the pushing time interval, pushing the target product to the corresponding target category user through the pushing channel.

7. An apparatus for business policy formulation, comprising:

8. The business strategy making apparatus according to claim 7, wherein the data obtaining module comprises:

the text cleaning submodule is used for removing the text which cannot be identified, the bad information text, the advertisement information text and the false information text in the service discussion text by using a preset word bank and an identification rule;

the text format processing submodule is used for modifying the font format of the rest service discussion text into a preset target font format;

and the text wrongly written character sub-module is used for modifying the wrongly written characters and the written characters in the rest service discussion texts according to a preset wrongly written character library and a written character library to obtain the standard service discussion texts.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the business strategy formulation method according to any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of formulating a business strategy according to any one of claims 1 to 6.