CN113627188A - New product discovery method, system, equipment and storage medium based on time sequence point process - Google Patents
New product discovery method, system, equipment and storage medium based on time sequence point process Download PDFInfo
- Publication number
- CN113627188A CN113627188A CN202110936863.XA CN202110936863A CN113627188A CN 113627188 A CN113627188 A CN 113627188A CN 202110936863 A CN202110936863 A CN 202110936863A CN 113627188 A CN113627188 A CN 113627188A
- Authority
- CN
- China
- Prior art keywords
- time
- products
- model
- product
- sound volume
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a system, equipment and a storage medium for discovering new products based on a time sequence point process, wherein the method comprises the following steps: acquiring text information in the related field including but not limited to a social platform, identifying products in the text information and historical data publishing time of the products, and sorting the products; establishing a strength function model in the time sequence point process according to 'product-publication time'; taking the sorted products and historical data release time of the products as training data, and calculating the optimal parameters of the intensity function model by using an EM (effective man) algorithm according to the maximum likelihood function; according to the calculated intensity function model, the sound volume intensity of the time point can be obtained by giving any future time point, the sound volume trend of each product is displayed in real time, and the analysis and decision-making of workers are facilitated. Through data learning of the sound volume development trend of new products on the social network, a large amount of labor cost is avoided.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method, a system, equipment and a storage medium for discovering new products based on a time sequence point process.
Background
In the information age, products are exploded, and new concept products emerge like bamboo shoots in spring after rain. However, for the manufacturers, how to find new products in time and grasp the dynamic state of the industry becomes a problem to be solved urgently.
The traditional new product discovery method is to collect data widely and obtain results through reading and analyzing by a large amount of manpower. However, this method requires a great labor cost and is very dependent on the professional analysis ability of a human.
Disclosure of Invention
Aiming at the technical problems of time consumption and labor consumption of the traditional new product discovery method, the invention provides a new product discovery method, a system, equipment and a storage medium based on a time sequence point process.
In a first aspect, an embodiment of the present application provides a method for discovering a new product based on a time sequence point process, including:
a data acquisition step: acquiring text information including but not limited to a social platform related field, identifying products in the text information and historical data publishing time of the products, and sorting the products;
a model establishing step: establishing a strength function model in the time sequence point process according to 'product-publication time';
model calculation: taking the sorted products and historical data release time of the products as training data, and calculating the optimal parameters of the intensity function model by applying an EM (effective man) algorithm according to a maximum likelihood function;
a new product prediction step: according to the calculated intensity function model, the sound volume intensity of the time point can be obtained by giving any future time point.
The method for discovering new products comprises the following steps:
a display step: and displaying the sound volume trend of each product in real time, and setting the top display of the product with the highest sound volume intensity ratio increase or the highest numerical value.
The method for discovering new products comprises the following steps:
and (3) updating the model: and continuously acquiring new text information, acquiring new training data through recognition and sorting, and continuously iteratively optimizing the intensity function model as supplementary training data.
In the method for discovering the new product, the intensity function model is established by adopting a Hawkes process in the step of establishing the model.
In a second aspect, an embodiment of the present application provides a new product discovery system based on a time-series point process, including:
a data acquisition unit: acquiring text information including but not limited to a social platform related field, identifying products in the text information and historical data publishing time of the products, and sorting the products;
a model establishing unit: establishing a strength function model in the time sequence point process according to 'product-publication time';
a model calculation unit: taking the sorted products and historical data release time of the products as training data, and calculating the optimal parameters of the intensity function model by applying an EM (effective man) algorithm according to a maximum likelihood function;
a new product prediction unit: according to the calculated intensity function model, the sound volume intensity of the time point can be obtained by giving any future time point.
The new product discovery system further includes:
a display unit: and displaying the sound volume trend of each product in real time, and setting the top display of the product with the highest sound volume intensity ratio increase or the highest numerical value.
The new product discovery system further includes:
a model updating unit: and continuously acquiring new text information, acquiring new training data through recognition and sorting, and continuously iteratively optimizing the intensity function model as supplementary training data.
In the new product discovery system, the model establishing unit establishes the strength function model by using a Hawkes process.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the processor implements the novelty discovery method according to the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the novelty discovery method according to the first aspect.
Compared with the prior art, the invention has the advantages and positive effects that:
1. the invention relates to a deep learning technology, which applies a time sequence point process to new product discovery, fully utilizes time information of new product sound volume, obtains the sound volume development trend of the new product, and avoids a large amount of labor cost.
2. The new product learning model has interpretability, can predict the sound volume development trend of the new product along with the time, and can be updated and adjusted along with continuous data acquisition.
Drawings
FIG. 1 is a schematic diagram illustrating steps of a method for discovering new products based on a time-series point process according to the present invention;
FIG. 2 is a block diagram of a novelty discovery system based on a time-series point process according to the present invention;
fig. 3 is a block diagram of a computer device according to an embodiment of the present application.
Wherein the reference numerals are:
1. a data acquisition unit; 2. a model building unit; 3. a model calculation unit; 4. a new product prediction unit; 5. a display unit; 6. a model updating unit; 81. a processor; 82. a memory; 83. a communication interface; 80. a bus.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
The present invention is described in detail with reference to the embodiments shown in the drawings, but it should be understood that these embodiments are not intended to limit the present invention, and those skilled in the art should understand that functional, methodological, or structural equivalents or substitutions made by these embodiments are within the scope of the present invention.
Before describing in detail the various embodiments of the present invention, the core inventive concepts of the present invention are summarized and described in detail by the following several embodiments.
According to the invention, the new product discovery model is established by adopting a time sequence point process theory, the sound volume development trend of the new product along with the time can be predicted based on the data on the social network, and the new product discovery model can be updated along with continuous data acquisition, so that a large amount of labor cost is avoided.
The first embodiment is as follows:
the time sequence point process is used for researching unequal interval time sequence problems, and predicting the occurrence probability of future events by considering a historical event model. Applying the time sequence point process theory to the new product discovery problem is a creative method.
Fig. 1 is a schematic step diagram of a method for discovering a new product based on a time sequence point process according to the present invention. As shown in fig. 1, this embodiment discloses a specific implementation of a new product discovery method (hereinafter referred to as "method") based on a time-series point process.
Specifically, the method disclosed in this embodiment mainly includes the following steps:
step S1: acquiring text information including but not limited to a social platform related field, identifying products in the text information and historical data publishing time of the products, and sorting the products;
specifically, product class entities in the text information are identified through a named entity identification (NER) model of a natural language processing technology, the publishing time of historical data of the product is sorted according to time sequence, and the product is finally sorted into a form of 'product- (publishing time 1) - - (publishing time 2) - - (publishing time N) - … … - (publishing time N').
Step S2: establishing a strength function model in the time sequence point process according to 'product-publication time';
specifically, the intensity function λ (t) in the process of constructing time series points according to the product-publication time is modeled as follows:
where μ represents the base intensity of the product's acoustic mass, function gθRepresenting the excitation function, using the Hawkes process, tiIs the historical data publication time for the product.
Step S3: taking the sorted products and historical data release time of the products as training data, and calculating the optimal parameters of the intensity function model by applying an EM (effective man) algorithm according to a maximum likelihood function;
the EM (Expectation-maximization) algorithm is also called an Expectation-maximization algorithm and is an iterative optimization strategy, and each iteration in the calculation method is divided into two steps, wherein one step is an Expectation step (E step) and the other step is a Maximum step (M step).
Step S4: according to the calculated intensity function model, the sound volume intensity of the time point can be obtained by giving any future time point.
Specifically, the sound volume trend of the product is obtained according to the sound volume intensities of different future time points, the sound volume trend of each product is displayed in real time, the top display of the product with the highest sound volume intensity ratio or the highest numerical value can be set, and relevant workers can conveniently make key analysis decisions.
Specifically, new text information is continuously acquired, new training data is obtained through recognition and sorting, and the new training data is used as supplementary training data to continuously optimize the intensity function model in an iterative mode.
The method for discovering the new product provided by the invention is used for mining the new product with great potential from massive data so that a user can grasp the product dynamics of the industry as soon as possible. Compared with the prior art, a large amount of labor is not needed; and the constructed new product discovery model can be interpreted and adjusted.
The application flow of the method is specifically described as follows:
1. data acquisition
The method comprises the steps of obtaining text information including but not limited to related fields of a social platform, obtaining product entity in the text information through a Named Entity Recognition (NER) model of a natural language processing technology, and finishing data obtaining.
Taking the makeup industry as an example, the obtained text data is as follows: "A dry skin" means the way that I thinks of Shenxian water. First, break the expression of dependence, i use a bottle and then do not use, have no dependence at all. Secondly, how dare to use miraculous water for a dried and sensitive skin? Because it is really very irritating. The things are that I only uses the acne in the place with the long closed mouth, and other effects I don't dare to say, but the effect of the wet dressing of the closed mouth acne is good. Third, i tried on sensitive cheeks, and indeed were somewhat painful, so abandoned paying attention to wet dressing to remove the occlusion. "through NER model, obtain entity" Shenxian water ", arrange and produce the final data:
"Shenxian water" (published time 1) - (published time 2) - (published time N) "wherein the times are in sequence.
2. Modeling
Constructing a new product discovery model, constructing an intensity function in the time sequence point process according to 'product-publication time', wherein lambda represents the intensity function of the sound volume of a product, and the model has the following form:
where μ represents the base intensity of the product's acoustic mass. Function gθRepresenting the excitation function, using the Hawkes process, tiIs the historical data publication time for the product.
3. Model calculation
And (3) taking the data acquired and sorted in the step (1) as training data, and calculating the optimal parameters of the intensity function model in the step (2) by applying an EM (effective noise) algorithm according to the maximum likelihood function so as to complete model calculation.
4. Predicting future trend of new product
According to the time-series point process theory, the intensity function represents the occurrence intensity of an event at the time t, and the sound volume intensity lambda (t) of the product at the time point can be obtained by the model calculated in the step 3 given any time point in the future.
5. Visual display
The sound volume trend prediction of each obtained new product can be displayed in real time, the top display with the fastest increase on the same ratio or the largest numerical value is set, and relevant workers can conveniently make key analysis decisions.
6. Model updating
Over time, step 1 will acquire new data, which can be used as supplementary training data to continue the iterative optimization model.
The basic idea of the invention is to solve the problem of finding new products by adopting a time sequence point process theory, and to avoid a large amount of labor cost by learning the development trend of the new products on the social network through data. The model has interpretability and can predict the sound volume development trend of the new product along with the time.
Example two:
in combination with the method for discovering new products based on the time-series point process disclosed in the first embodiment, this embodiment discloses a specific implementation example of a new product discovery system (hereinafter referred to as "system") based on the time-series point process.
Referring to fig. 2, the system includes:
the data acquisition unit 1: acquiring text information including but not limited to a social platform related field, identifying products in the text information and historical data publishing time of the products, and sorting the products;
model creation unit 2: establishing a strength function model in the time sequence point process according to 'product-publication time';
specifically, in the model establishing unit 2, the intensity function model is established by using a Hawkes process.
The model calculation unit 3: taking the sorted products and historical data release time of the products as training data, and calculating the optimal parameters of the intensity function model by applying an EM (effective man) algorithm according to a maximum likelihood function;
new product prediction unit 4: according to the calculated intensity function model, the sound volume intensity of the time point can be obtained by giving any future time point.
The display unit 5: and displaying the sound volume trend of each product in real time, and setting the top display of the product with the highest sound volume intensity ratio increase or the highest numerical value.
The model updating unit 6: and continuously acquiring new text information, acquiring new training data through recognition and sorting, and continuously iteratively optimizing the intensity function model as supplementary training data.
The invention applies the time sequence point process to the discovery of new products, fully utilizes the time information of the sound volume of the new products, can give out the dynamic sound volume development trend and is convenient for relevant working personnel to analyze and decide the new products.
For a system for discovering a new product based on a time sequence point process disclosed in this embodiment and a technical solution of the rest of the same parts in a method for discovering a new product based on a time sequence point process disclosed in the first embodiment, please refer to the description of the first embodiment, and details are not repeated herein.
Example three:
referring to FIG. 3, the embodiment discloses an embodiment of a computer device. The computer device may comprise a processor 81 and a memory 82 in which computer program instructions are stored.
Specifically, the processor 81 may include a Central Processing Unit (CPU), or A Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
The memory 82 may be used to store or cache various data files for processing and/or communication use, as well as possible computer program instructions executed by the processor 81.
The processor 81 implements any of the novelty discovery methods in the above embodiments by reading and executing computer program instructions stored in the memory 82.
In some of these embodiments, the computer device may also include a communication interface 83 and a bus 80. As shown in fig. 3, the processor 81, the memory 82, and the communication interface 83 are connected via the bus 80 to complete communication therebetween.
The communication interface 83 is used for implementing communication between modules, devices, units and/or equipment in the embodiment of the present application. The communication port 83 may also be implemented with other components such as: the data communication is carried out among external equipment, image/data acquisition equipment, a database, external storage, an image/data processing workstation and the like.
In addition, in combination with the novelty discovery method in the above embodiments, the embodiments of the present application may provide a computer-readable storage medium to implement. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the novelty discovery methods of the above embodiments.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
In conclusion, the method has the advantages that the time sequence point process is applied to new product discovery, the time information of the sound volume of the new product is fully utilized, the sound volume development trend of the new product is obtained, and a large amount of labor cost is avoided; the new product learning model has interpretability, can predict the sound volume development trend of the new product along with the time, and can be updated and adjusted along with continuous data acquisition.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A new product discovery method based on a time sequence point process is characterized by comprising the following steps:
a data acquisition step: acquiring text information including but not limited to a social platform related field, identifying products in the text information and historical data publishing time of the products, and sorting the products;
a model establishing step: establishing a strength function model in the time sequence point process according to 'product-publication time';
model calculation: taking the sorted products and historical data release time of the products as training data, and calculating the optimal parameters of the intensity function model by applying an EM (effective man) algorithm according to a maximum likelihood function;
a new product prediction step: according to the calculated intensity function model, the sound volume intensity of the time point can be obtained by giving any future time point.
2. The novelty discovery method of claim 1 further comprising:
a display step: and displaying the sound volume trend of each product in real time, and setting the top display of the product with the highest sound volume intensity ratio increase or the highest numerical value.
3. The novelty discovery method of claim 2 further comprising:
and (3) updating the model: and continuously acquiring new text information, acquiring new training data through recognition and sorting, and continuously iteratively optimizing the intensity function model as supplementary training data.
4. The novelty discovery method of claim 1 wherein said modeling step uses a Hawkes process to model said intensity function.
5. A novelty discovery system based on a time-series point process, comprising:
a data acquisition unit: acquiring text information including but not limited to a social platform related field, identifying products in the text information and historical data publishing time of the products, and sorting the products;
a model establishing unit: establishing a strength function model in the time sequence point process according to 'product-publication time';
a model calculation unit: taking the sorted products and historical data release time of the products as training data, and calculating the optimal parameters of the intensity function model by applying an EM (effective man) algorithm according to a maximum likelihood function;
a new product prediction unit: according to the calculated intensity function model, the sound volume intensity of the time point can be obtained by giving any future time point.
6. The novelty discovery system of claim 5 further comprising:
a display unit: and displaying the sound volume trend of each product in real time, and setting the top display of the product with the highest sound volume intensity ratio increase or the highest numerical value.
7. The novelty discovery system of claim 6 further comprising:
a model updating unit: and continuously acquiring new text information, acquiring new training data through recognition and sorting, and continuously iteratively optimizing the intensity function model as supplementary training data.
8. The novelty discovery system of claim 5 wherein said model building unit uses the Hawkes process to build said strength function model.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the novelty discovery method of any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a novelty discovery method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110936863.XA CN113627188A (en) | 2021-08-16 | 2021-08-16 | New product discovery method, system, equipment and storage medium based on time sequence point process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110936863.XA CN113627188A (en) | 2021-08-16 | 2021-08-16 | New product discovery method, system, equipment and storage medium based on time sequence point process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113627188A true CN113627188A (en) | 2021-11-09 |
Family
ID=78385645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110936863.XA Pending CN113627188A (en) | 2021-08-16 | 2021-08-16 | New product discovery method, system, equipment and storage medium based on time sequence point process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627188A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657962A (en) * | 2018-12-13 | 2019-04-19 | 洛阳博得天策网络科技有限公司 | A kind of appraisal procedure and system of the volume assets of brand |
| CN109993566A (en) * | 2018-01-03 | 2019-07-09 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus for predicting product objective data |
| CN110738414A (en) * | 2019-10-15 | 2020-01-31 | 北京明略软件系统有限公司 | risk prediction method and device and computer readable storage medium |
| CN112182216A (en) * | 2020-09-28 | 2021-01-05 | 时趣互动（北京）科技有限公司 | Marketing hotspot trend prediction method and device |
| CN112818219A (en) * | 2021-01-22 | 2021-05-18 | 北京明略软件系统有限公司 | Method, system, electronic device and readable storage medium for explaining recommendation effect |
-
2021
- 2021-08-16 CN CN202110936863.XA patent/CN113627188A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993566A (en) * | 2018-01-03 | 2019-07-09 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus for predicting product objective data |
| CN109657962A (en) * | 2018-12-13 | 2019-04-19 | 洛阳博得天策网络科技有限公司 | A kind of appraisal procedure and system of the volume assets of brand |
| CN110738414A (en) * | 2019-10-15 | 2020-01-31 | 北京明略软件系统有限公司 | risk prediction method and device and computer readable storage medium |
| CN112182216A (en) * | 2020-09-28 | 2021-01-05 | 时趣互动（北京）科技有限公司 | Marketing hotspot trend prediction method and device |
| CN112818219A (en) * | 2021-01-22 | 2021-05-18 | 北京明略软件系统有限公司 | Method, system, electronic device and readable storage medium for explaining recommendation effect |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109671020B (en) | Image processing method, device, electronic equipment and computer storage medium | |
| CN108229419A (en) | For clustering the method and apparatus of image | |
| CN112257578B (en) | Face key point detection method and device, electronic equipment and storage medium | |
| CN112418059B (en) | Emotion recognition method and device, computer equipment and storage medium | |
| CN111738403B (en) | Neural network optimization method and related equipment | |
| CN113822207B (en) | Hyperspectral remote sensing image identification method and device, electronic equipment and storage medium | |
| CN111553215A (en) | Personnel association method and device, and graph convolution network training method and device | |
| WO2019085332A1 (en) | Financial data analysis method, application server, and computer readable storage medium | |
| CN110751021A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
| CN114037478A (en) | Advertisement abnormal flow detection method and system, electronic equipment and readable storage medium | |
| CN111931848B (en) | Data feature extraction method and device, computer equipment and storage medium | |
| CN113869496A (en) | Acquisition method of neural network, data processing method and related equipment | |
| CN112884569A (en) | Credit assessment model training method, device and equipment | |
| CN115859302A (en) | Source code vulnerability detection method, device, equipment and storage medium | |
| CN111414343B (en) | Log writing method, device, electronic equipment and medium | |
| CN113627188A (en) | New product discovery method, system, equipment and storage medium based on time sequence point process | |
| CN112348188A (en) | Model generation method and device, electronic device and storage medium | |
| CN111353577B (en) | Multi-task-based cascade combination model optimization method and device and terminal equipment | |
| CN116503608A (en) | Data distillation method based on artificial intelligence and related equipment | |
| CN106156568B (en) | Biological information identification module and electronic equipment | |
| EP3975071A1 (en) | Identifying and quantifying confounding bias based on expert knowledge | |
| CN111449646B (en) | Electrocardiogram identification method and device, storage medium and electronic equipment | |
| CN113643283A (en) | Method, device, equipment and storage medium for detecting aging condition of human body | |
| CN109614854B (en) | Video data processing method and device, computer device and readable storage medium | |
| CN115879524A (en) | Model training method and related equipment thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |